Jobs in Germany - Jubil Jobs

Staff / Senior Software Engineer (Agentic Search) - Runtime

Nebius

Location: Zurich

<div class="content-intro">About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.</div>The Product In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible. We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale. The Role We are looking for a Senior Software Engineer to work on the runtime systems of a novel search engine tailored for agentic AI consumption. In this role, you will focus on building low-latency, high-throughput systems that serve search queries in real time. You will work on the critical path of user-facing requests, where performance, predictability, and efficiency directly impact product quality. You will design and operate systems that handle thousands of requests per second under strict latency budgets, optimising every layer from request handling to data access and response assembly. In this position, your responsibility will be to <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="whitespace-normal break-words pl-2">Design, implement, and operate core runtime services for serving search queries at scale</li> <li class="whitespace-normal break-words pl-2">Build and optimise request flows, including query processing, retrieval orchestration, and response assembly under strict latency budgets</li> <li class="whitespace-normal break-words pl-2">Develop systems that maintain performance and predictability under high load</li> <li class="whitespace-normal break-words pl-2">Optimise CPU, memory, and data access patterns in performance-critical paths</li> <li class="whitespace-normal break-words pl-2">Ensure reliability, observability, and predictability across production services</li> <li class="whitespace-normal break-words pl-2">Build well-tested systems with clear responsibilities and interaction contracts, while remaining flexible as architecture evolves</li> <li class="whitespace-normal break-words pl-2">Define and implement observability primitives, including structured logs, metrics, traces, and latency breakdowns</li> <li class="whitespace-normal break-words pl-2">Monitor throughput, latency, and resource usage, and drive improvements in performance and cost efficiency</li> <li class="whitespace-normal break-words pl-2">Collaborate with indexing and ML teams to integrate retrieval and ranking components, keeping ML logic decoupled from core system internals</li> <li class="whitespace-normal break-words pl-2">Support experimentation and iteration through controlled rollouts and rigorous benchmarking</li> </ul> You may be a good fit if you: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="whitespace-normal break-words pl-2">Have 5+ years of experience as a software engineer working on production backend systems</li> <li class="whitespace-normal break-words pl-2">Have strong hands-on expertise in C++ or Rust in real-world, high-load services</li> <li class="whitespace-normal break-words pl-2">Have built and operated high-load, low-latency user-facing systems handling thousands of RPS under strict latency constraints</li> <li class="whitespace-normal break-words pl-2">Understand performance at a systems level — CPU, memory, networking, and data access</li> <li class="whitespace-normal break-words pl-2">Have operated your own code in production: deployed it, debugged incidents, and rolled back changes when necessary</li> <li class="whitespace-normal break-words pl-2">Think end-to-end about request flows rather than staying within isolated components</li> <li class="whitespace-normal break-words pl-2">Can balance correctness, latency, and development velocity, making pragmatic tradeoffs when scope or time requires</li> <li class="whitespace-normal break-words pl-2">Collaborate effectively across engineering, ML, and product teams, communicating clearly in cross-functional settings</li> </ul> Strong candidates may also have experience with: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="whitespace-normal break-words pl-2">DBMS internals (open source or SaaS) and cloud infrastructure</li> <li class="whitespace-normal break-words pl-2">High-load web applications or large-scale APIs</li> <li class="whitespace-normal break-words pl-2">Performance-critical systems such as trading platforms or real-time data pipelines</li> <li class="whitespace-normal break-words pl-2">Low-level performance tuning and hardware-level optimisation</li> <li class="whitespace-normal break-words pl-2">Open-source contributions or active involvement in the engineering community</li> <li class="whitespace-normal break-words pl-2">Competitive programming or CTF participation</li> <li class="whitespace-normal break-words pl-2">SHAD or similar advanced technical programmes</li> <li class="whitespace-normal break-words pl-2">Conference talks or technical publications</li> </ul> We conduct coding interviews as part of the process.<div class="content-conclusion">Benefits & Perks: <ul> <li>Competitive compensation</li> <li>Career growth and learning opportunities</li> <li>Flexibility and ownership</li> <li>Collaborative and innovative culture</li> <li>Opportunity to work on impactful AI projects</li> <li>International environment and talented teams</li> </ul> What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI  Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.  If you need accommodations during the application process, please let us know.</div>

Find more English Speaking Jobs in Switzerland on Arbeitnow

Agentic Search

View Job

Published: September 28, 2026

Staff / Senior Software Engineer (Agentic Search) - Index

Nebius

Location: Zurich

<div class="content-intro">About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.</div>The Product In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible. We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale. The Role We are looking for a Senior Software Engineer to work on the indexing and data processing layer of a novel search engine tailored for agentic AI consumption. In this role, you will focus on building systems that ingest, process, and organise massive volumes of data into efficient, queryable structures. You will work primarily on offline and nearline pipelines, ensuring that data is fresh, complete, and efficiently accessible by downstream retrieval systems. You will operate in an environment where throughput, scalability, and correctness are critical; designing systems capable of handling tens of gigabytes per second across continuously evolving datasets. In this position, your responsibility will be to: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li>Design, implement, and operate large-scale indexing systems and data pipelines that sit at the core of our search infrastructure</li> <li>Develop and optimise indexing strategies balancing performance, freshness, and resource efficiency</li> <li>Work on storage formats, compaction strategies, and update mechanisms to keep data accessible and current</li> <li>Ensure reliability and predictability of pipelines under high-throughput conditions</li> <li>Build well-tested components with clear responsibilities and interaction contracts, while remaining flexible as the system evolves</li> <li>Define and implement observability primitives, including structured logs, metrics, and data quality signals across offline and nearline pipelines</li> <li>Monitor throughput, resource usage, and cost, and drive optimisations when business needs require it</li> <li>Collaborate with runtime and ML teams to ensure indexing outputs meet retrieval and ranking requirements</li> <li>Enable safe experimentation on indexing strategies and data processing logic through controlled rollouts and clearly defined quality signals</li> </ul> You may be a good fit if you: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li>5+ years of experience building production backend or data infrastructure systems</li> <li>Strong Go experience (C++/Rust is a plus)</li> <li>Experience with large-scale data processing systems (10+ GiB/sec throughput, petabyte-scale datasets, etc.)</li> <li>Experience building or operating databases, storage systems, data planes, or indexing pipelines</li> <li>Strong understanding of distributed systems, fault tolerance, consistency, and scalability</li> <li>Experience running production systems and handling operational incidents</li> <li>Systems-thinking mindset and ability to reason about end-to-end data flows</li> </ul> Strong candidates may also have experience with: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="whitespace-normal break-words pl-2">Distributed data processing frameworks such as Spark, Flink, MapReduce, or Beam</li> <li class="whitespace-normal break-words pl-2">Content systems including, scraping, proxying, or anti-bot infrastructure</li> <li class="whitespace-normal break-words pl-2">Ad tech, social networks, or other large-scale content platforms</li> <li class="whitespace-normal break-words pl-2">DBMS internals (open source or SaaS) and cloud infrastructure</li> <li class="whitespace-normal break-words pl-2">Open-source contributions or active involvement in the engineering community</li> <li class="whitespace-normal break-words pl-2">Competitive programming or CTF participation (ICPC, IOI, or similar)</li> <li class="whitespace-normal break-words pl-2">SHAD or similar advanced technical programmes</li> <li class="whitespace-normal break-words pl-2">Conference talks or technical publications</li> </ul>   We conduct coding interviews as part of the process.<div class="content-conclusion">Benefits & Perks: <ul> <li>Competitive compensation</li> <li>Career growth and learning opportunities</li> <li>Flexibility and ownership</li> <li>Collaborative and innovative culture</li> <li>Opportunity to work on impactful AI projects</li> <li>International environment and talented teams</li> </ul> What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI  Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.  If you need accommodations during the application process, please let us know.</div>

Find Jobs in Switzerland on Arbeitnow

Agentic Search

View Job

Published: September 28, 2026

Staff / Senior Software Engineer (Agentic Search) - Crawler

Nebius

Location: Zurich

<div class="content-intro">About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.</div>The Product In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible. We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale. <h4>The Role</h4> We are looking for a Senior Software Engineer to work on the content acquisition and crawling infrastructure of a novel search engine tailored for agentic AI consumption. In this role, you will focus on building systems that discover, fetch, and continuously refresh content from the open web and other large-scale data sources. You will design distributed crawling, scheduling, and ingestion infrastructure capable of operating at internet scale while balancing coverage, freshness, resource efficiency, and reliability. You will work on systems that process billions of URLs, manage high-throughput data flows, and ensure that high-quality content is consistently available to downstream indexing and retrieval systems. In this position, your responsibility will be to: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li>Design, implement, and operate web-scale crawling systems for acquiring content from the internet</li> <li>Build ingestion workflows for internal and external data sources, including crawlers, structured feeds, and partner integrations</li> <li>Develop crawl scheduling, prioritisation, recrawl policies, and freshness strategies</li> <li>Build systems for URL discovery, deduplication, content extraction, and crawl orchestration</li> <li>Ensure reliable operation of crawling infrastructure under high-throughput conditions</li> <li>Define observability and quality metrics for crawl coverage, freshness, throughput, and content quality</li> <li>Monitor resource usage, bandwidth consumption, and infrastructure cost</li> <li>Collaborate with indexing and ML teams to ensure acquired content meets retrieval and ranking requirements</li> <li>Enable safe experimentation with crawling strategies and content acquisition policies</li> </ul> You may be a good fit if you: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li>5+ years of experience building backend or distributed systems</li> <li>Strong Go or C++ expertise </li> <li>Experience with large-scale distributed systems (10k+ RPS, billions of URLs, high-throughput pipelines)</li> <li>Understanding of web protocols (HTTP, DNS, TLS), crawling, scraping, and content extraction</li> <li>Experience operating production systems and debugging failures in distributed environments</li> <li>Strong understanding of scalability, fault tolerance, and resource management</li> </ul> Strong candidates may also have experience with: <ul class="[li_&]:mb-0 [li_&]:mt-1 [li_&]:gap-1 [&:not(:last-child)_ul]:pb-1 [&:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li>Web crawling</li> <li>Building streaming data pipelines and event-driven systems</li> <li>Kafka, Pulsar, NATS, RabbitMQ, or similar messaging platforms</li> <li>Designing distributed schedulers, queues, and asynchronous processing systems</li> <li>Spark, Flink, Beam, or MapReduce</li> <li>Ad tech, social networks, search engines, or other large-scale content platforms</li> </ul> We conduct coding interviews as part of the process.<div class="content-conclusion">Benefits & Perks: <ul> <li>Competitive compensation</li> <li>Career growth and learning opportunities</li> <li>Flexibility and ownership</li> <li>Collaborative and innovative culture</li> <li>Opportunity to work on impactful AI projects</li> <li>International environment and talented teams</li> </ul> What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI  Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.  If you need accommodations during the application process, please let us know.</div>

Find more English Speaking Jobs in Switzerland on Arbeitnow

Agentic Search

View Job

Published: September 28, 2026

Staff / Principal Applied AI Researcher (Agentic Search)

Nebius

Location: Zurich

<div class="content-intro">About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.</div>  We are seeking a Staff or Principal Applied AI Researcher to join a fast growing team building an agent native search platform - the web access layer for AI systems. You can think of this as Google for AI agents: a system designed for machines, not humans. We are building agentic search, where AI systems actively plan, retrieve, evaluate, and refine information rather than simply returning results. As AI becomes the primary interface to the web, this layer will replace the role of traditional search engines. We are designing how AI agents - not humans - retrieve, evaluate, and reason over web data in real time, under strict latency and reliability constraints. This means solving retrieval and ranking under entirely new access patterns and at significant scale, with systems operating over constantly changing, unstructured data and serving tens of thousands of production workloads 24 by 7. This role comes with ownership over key parts of our applied AI research direction and system design, with a strong expectation of defining new approaches and shipping measurable impact in production. What you'll work on: <ul data-start="2122" data-end="2433"> <li data-section-id="1t8ch56" data-start="2122" data-end="2228">Designing agent native retrieval systems optimised for machine consumption rather than human search UX</li> <li data-section-id="1vyyyl2" data-start="2229" data-end="2317">Building systems where LLMs iteratively plan, query, refine, and reason over results</li> <li data-section-id="u2e4jn" data-start="2318" data-end="2433">Developing ranking and retrieval approaches for multi step, agent driven workflows under real world constraints</li> </ul> Your responsibilites: <ul data-start="2466" data-end="3318"> <li data-section-id="ikn80n" data-start="2466" data-end="2553">Drive applied research and technical direction across retrieval and ranking systems</li> <li data-section-id="1d43g6p" data-start="2554" data-end="2676">Design and evolve multi stage retrieval architectures (query understanding, rewriting, reranking, iterative retrieval)</li> <li data-section-id="5nesg" data-start="2677" data-end="2746">Develop methods for grounding LLMs in real time web data at scale</li> <li data-section-id="ai5hot" data-start="2747" data-end="2874">Define and implement new evaluation paradigms and metrics for agentic systems, where correctness is not reducible to clicks</li> <li data-section-id="cw6cfi" data-start="2875" data-end="3000">Lead experimentation on modern retrieval approaches (embeddings, hybrid search, reranking) and bring them into production</li> <li data-section-id="reun61" data-start="3001" data-end="3068">Analyse trade-offs across relevance, latency, and cost at scale</li> <li data-section-id="plykg2" data-start="3069" data-end="3165">Work closely with engineering to deploy systems in high throughput, low latency environments</li> <li data-section-id="982sm" data-start="3166" data-end="3252">Own ambiguous problems end to end and contribute to product and research direction</li> <li data-section-id="1f9xzot" data-start="3253" data-end="3318">Mentor engineers and help raise the technical bar of the team</li> </ul> Must haves: <ul data-start="3340" data-end="3986"> <li data-section-id="18rk41c" data-start="3340" data-end="3409">8+ years of experience in applied AI, ML, or software engineering</li> <li data-section-id="1ui6jyu" data-start="3410" data-end="3485">Proven track record of shipping ML or AI systems to production at scale</li> <li data-section-id="1pkac7v" data-start="3486" data-end="3576">Deep experience with search, retrieval, ranking, recommendation systems, or assistants</li> <li data-section-id="1j0ih3f" data-start="3577" data-end="3665">Strong understanding of modern deep learning, especially transformers and embeddings</li> <li data-section-id="1oq4qli" data-start="3666" data-end="3731">Experience with LLM integrated or knowledge intensive systems</li> <li data-section-id="1hq4cp9" data-start="3732" data-end="3805">Experience designing evaluation frameworks and metrics for ML systems</li> <li data-section-id="czwkc8" data-start="3806" data-end="3885">Strong programming skills in Python and at least one of Go, C++, or similar</li> <li data-section-id="oj9bth" data-start="3886" data-end="3986">Ability to operate in a fast moving, product driven environment with high ownership and autonomy</li> </ul> Nice to haves <ul data-start="4011" data-end="4292"> <li data-section-id="1wjy3b1" data-start="4011" data-end="4075">Experience with large scale search or recommendation systems</li> <li data-section-id="s66hyu" data-start="4076" data-end="4153">Background in agentic AI systems (agents, tool use, autonomous workflows)</li> <li data-section-id="1ri8v8b" data-start="4154" data-end="4212">Experience with RAG, multi step retrieval, or tool use</li> <li data-section-id="fdjncx" data-start="4213" data-end="4292">Publications, open source, or similar signals of technical depth and impact</li> </ul>  <div class="content-conclusion">Benefits & Perks: <ul> <li>Competitive compensation</li> <li>Career growth and learning opportunities</li> <li>Flexibility and ownership</li> <li>Collaborative and innovative culture</li> <li>Opportunity to work on impactful AI projects</li> <li>International environment and talented teams</li> </ul> What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI  Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.  If you need accommodations during the application process, please let us know.</div>

Find Jobs in Switzerland on Arbeitnow

Agentic Search

View Job

Published: September 28, 2026

Senior Machine Learning Engineer, LLM Inference Optimization

Nebius

Location: Zurich

<div class="content-intro">About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.</div><h3>The role </h3> Nebius Token Factory is building fast, reliable, and cost-efficient inference services for frontier models. As a Senior Machine Learning Engineer on our Applied AI team, you will own model and endpoint optimization from model artifacts through production deployment. Your work will span model internals, inference engines, serving architecture, and benchmarking, with a focus on improving latency, throughput, memory efficiency, GPU utilization, and cost per token while maintaining model quality and reliability. This is a hands-on role in which you will work on complex optimization projects, diagnose difficult serving problems, and deliver measurable improvements in production. Working closely with kernel and platform engineers, you will evaluate serving configurations, resolve performance and quality regressions, and optimize inference for real-world workloads, supported by reproducible benchmarks and safe production rollouts. Your responsibilities:  <ul> <li> Own optimization work for specific model families, customer endpoints, or serving backends. </li> <li> Run engine comparisons and recommend practical serving configurations for specific workloads. </li> <li> Debug model quality or performance regressions during production rollouts. </li> <li> Optimize LLM and VLM endpoints for latency, throughput, memory efficiency, GPU utilization, quality, and cost per token. </li> <li> Deploy, configure, benchmark, and extend inference engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, or similar systems. </li> <li> Build and productionize model-compression workflows, including quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery. </li> <li> Implement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving. </li> <li> Build reproducible benchmark harnesses for TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token. </li> <li> Partner with GPU kernel engineers and platform engineers to diagnose bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. </li> <li> Write clear design docs, performance reports, rollout plans, and customer-facing technical explanations. </li> </ul> Must-haves:  <ul> <li> Strong Python and PyTorch engineering skills. </li> <li> Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference systems. </li> <li> Practical knowledge of at least one modern inference stack such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or equivalent internal systems. </li> <li> Strong understanding of transformer inference bottlenecks, including KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. </li> <li> Ability to reason quantitatively about latency, throughput, quality, utilization, and cost tradeoffs. </li> <li> Strong communication skills and ability to collaborate with research, kernel, infrastructure, product, and customer teams. </li> </ul> Nice-to-haves:  <ul> <li> Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, SmoothQuant, or related techniques. </li> <li> Experience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or other inference acceleration methods. </li> <li> Experience with agentic workloads, including tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. </li> <li> CUDA or Triton familiarity, even if the role is not primarily a kernel-engineering role. </li> <li> Open-source contributions to vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, KServe, or related projects. </li> </ul> <h3> </h3><div class="content-conclusion">Benefits & Perks: <ul> <li>Competitive compensation</li> <li>Career growth and learning opportunities</li> <li>Flexibility and ownership</li> <li>Collaborative and innovative culture</li> <li>Opportunity to work on impactful AI projects</li> <li>International environment and talented teams</li> </ul> What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI  Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire.  If you need accommodations during the application process, please let us know.</div>

Find Jobs in Switzerland on Arbeitnow

ML

View Job

Published: September 28, 2026