Senior Machine Learning Engineer, LLM Inference Optimization

ph3About Nebius: /h3 /brpNebius 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 /brpBuilt 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 /brpListed 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 /brh3The role /h3 /brpNebius 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. /p /brpThis 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. /p /brh3Your responsibilities: /h3 /brul /brliOwn optimization work for specific model families, customer endpoints, or serving backends. /li /brliRun engine comparisons and recommend practical serving configurations for specific workloads. /li /brliDebug model quality or performance regressions during production rollouts. /li /brliOptimize LLM and VLM endpoints for latency, throughput, memory efficiency, GPU utilization, quality, and cost per token. /li /brliDeploy, configure, benchmark, and extend inference engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, or similar systems. /li /brliBuild and

productionize model-compression workflows, including quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery. /li /brliImplement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving. /li /brliBuild reproducible benchmark harnesses for TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token. /li /brliPartner with GPU kernel engineers and platform engineers to diagnose bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. /li /brliWrite clear design docs, performance reports, rollout plans, and customer-facing technical explanations. /li /br /ul /brh3Must-haves: /h3 /brul /brliStrong Python and PyTorch engineering skills. /li /brliHands-on experience

deploying or optimizing LLM, VLM, or high-throughput transformer inference systems. /li /brliPractical 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 /brliStrong understanding of transformer inference bottlenecks, including KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. /li /brliAbility to reason quantitatively about latency, throughput, quality, utilization, and cost tradeoffs. /li /brliStrong communication skills and ability to collaborate with research, kernel, infrastructure, product, and customer teams. /li /br /ul /brh3Nice-to-have: /h3 /brul /brliExperience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, SmoothQuant, or related techniques. /li

/brliExperience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or other inference acceleration methods. /li /brliExperience with agentic workloads, including tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. /li /brliCUDA or Triton familiarity, even if the role is not primarily a kernel-engineering role. /li /brliOpen-source contributions to vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, KServe, or related projects. /li /br /ul /brh3Benefits Perks: /h3 /brul /brliCompetitive compensation /li /brliCareer growth and learning opportunities /li /brliFlexibility and ownership /li /brliCollaborative and innovative culture /li /brliOpportunity to work on impactful AI projects /li /brliInternational environment and talented teams /li /br /ul /brh3What's it like to work at Nebius: /h3 /brpFast

moving- Bold thinking- Constant growth- Meaningful impact- Trust and real ownership- Opportunity to shape the future of AI /p /brh3Equal Opportunity Statement: /h3 /brpNebius 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 /brpApplicants 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 /brpIf you need accommodations during the application process, please let us know. /p /p