Senior Machine Learning Engineer, LLM Inference Optimization (opens in a new tab) Zurich

pbAbout Nebius: /b /p pNebius 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. /p pBuilt by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. /p pListed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with RD 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 RD. /p h3The role /h3 pAs a Senior Machine Learning Engineer onthe Applied AI team at Nebius Token Factory,you will own model and endpoint optimization from model artifacts through production deployment. Your work will span model internals,quantization and model compression, speculative decoding, KV-cache optimization,inference engines, serving architecture, andbenchmarking to improvelatency, throughput, memory efficiency, GPU utilization, and cost per token whilepreservingquality and reliability. /p pYouwill work with kernel and platformengineers to investigate serving problems, compare configurations, andresolve performance and qualityregressions. You will evaluate model- and engine-level optimizations together with distributed inference designs, including request routing, scheduling, prefill/decode coordination, and multi-node GPU execution. Your improvements will be validated throughreproducible benchmarks and safe productionrollouts under real-world workloads. /p h3Your responsibilities /h3 ul liOwn optimizationprojectsfor specific model families, customer endpoints, or serving backends. /li liCompare inference enginesand recommend serving configurationssuited to individualworkloads. /li liDiagnose model-quality andperformance regressions during production rollouts. /li liImproveLLM and VLMendpointlatency, throughput, memory efficiency, GPU utilization, quality, and cost per token. /li liDeploy, configure, benchmark, and extend engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server,and NVIDIA Dynamo. /li liDevelop production model-compression workflows coveringquantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery. /li liImplement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving.For prefill–decode disaggregation (PDD), evaluate KV-cache transfer, worker placement, and capacity balancing to determine which workloads benefit from the architecture. /li liDesign and improve LLM request routers and scheduling policies that balance worker utilization, queueing, request characteristics, and KV-cache locality while meeting latency and reliability targets. /li liScale dense and mixture-of-experts inference across multiple GPU nodes. Select and tune tensor, pipeline, data, and expert parallelism—including wide expert parallelism (WideEP)—with attention to hardware topology, expert load balance, and communication overhead. /li liBuild reproducible benchmark harnessesmeasuringTTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token.Validate architecture choices under representative traffic and consistent GPU budgets. /li liCollaboratewith GPU kernel and platform engineers totracebottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. /li liProduce design documents,performance reports, rollout plans, and customer-facing technical explanations. /li /ul h3Must-haves /h3 ul liStrongengineering skills in Python and PyTorch. /li liHands-on experience deploying or optimizing LLM, VLM, or high-throughput transformerinference. /li liPractical knowledge of at least one modern inferencestack,such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, oran equivalent internal system. /li liA strongunderstanding of transformer inferencebottlenecks involvingKV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. /li liAbility toquantify trade-offs amonglatency, throughput, quality, utilization, andcost. /li liExperience designing or optimizing distributed inference system architecture, with hands-on work in one or more areas such as request routing, distributed scheduling, PDD, multi-node inference, or expert parallelism. /li liStrong communication andcollaboration skills acrossresearch, kernel, infrastructure, product, and customer teams. /li /ul h3Nice-to-haves /h3 ul liExperience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, orSmoothQuant. /li liExperience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, orrelatedinference acceleration methods. /li liExperiencesupporting agentic workloads involvingtool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. /li liFamiliarity with CUDA or Triton; the role does not require kernel engineering to be the candidate’s primary specialization. /li liContributions to open-source projects such asvLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, orKServe. /li liImplementation experience with cache-aware request routing, PDD, or WideEP, including diagnosing communication bottlenecks and load imbalance. /li liFamiliarity with GPU communication libraries and interconnects, such as NCCL, NVLink, InfiniBand, or RoCE. /li /ul pbBenefits Perks: /b /p ul liCompetitive compensation /li liCareer growth and learning opportunities /li liFlexibility and ownership /li liCollaborative and innovative culture /li liOpportunity to work on impactful AI projects /li liInternational environment and talented teams /li /ul pbWhat's it like to work at Nebius: /b /p pFast moving- Bold thinking- Constant growth- Meaningful impact- Trust and real ownership- Opportunity to shape the future of AI /p pbEqual Opportunity Statement: /b /p pNebius 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. /p pApplicants 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. /p pIf you need accommodations during the application process, please let us know. /p #J-18808-Ljbffr