[All remote jobs](https://jobicy.com/jobs.md)[![Nebius logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/d90c0566-221.webp)](https://jobicy.com/company/nebius.md)[Nebius](https://jobicy.com/company/nebius.md) # Senior Machine Learning Engineer, LLM Inference Optimization Review the role, location requirements, compensation details, and application process before deciding whether this opportunity fits your next career move. [Apply for this job](#job-application)[View company](https://jobicy.com/company/nebius.md)ShareRemote from[Europe](https://jobicy.com/job-region/europe.md), [Israel](https://jobicy.com/job-region/israel.md)SalaryUndisclosedDepartment[Software Engineering](https://jobicy.com/categories/engineering.md)EmploymentFull TimeExperienceSeniorPublished27 Oct 2026Apply before26 Nov 2026Listing views29Application actions3Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. AI Summary ## The role, at a glance. Nebius is seeking a senior machine learning engineer to optimize LLM and VLM inference from model artifacts through reliable production deployment. The role focuses on quantization, compression, speculative decoding, KV-cache management, distributed serving, routing, scheduling, and multi-node GPU execution. The engineer will benchmark and improve latency, throughput, GPU utilization, memory efficiency, quality, and cost per token using platforms such as vLLM, SGLang, TensorRT-LLM, and Triton Inference Server. Close collaboration with kernel, infrastructure, product, and customer-facing teams is central to diagnosing bottlenecks and safely rolling out performance improvements. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 5/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThis is an advanced systems-ML role requiring deep practical expertise in transformer inference, GPU performance trade-offs, distributed execution, and production reliability. Success depends on independently converting benchmark evidence into architecture and rollout decisions across multiple technical layers. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job median (per year)Market rate$190,000US market range (per year)$160k–$250k0$275k AI insightThe yearly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer salary was disclosed. Estimated annual USD market compensation for a senior LLM inference optimization engineer is $160,000–$250,000, with an estimated midpoint of $190,000; this is an AI estimate rather than verified employer compensation. ## Core skills Skills and capabilities most closely associated with this opportunity. [Python](https://jobicy.com/jobs?search_keywords=Python.md)[PyTorch](https://jobicy.com/jobs?search_keywords=PyTorch.md)[LLM inference optimization](https://jobicy.com/jobs?search_keywords=LLM%20inference%20optimization.md)[Transformer serving](https://jobicy.com/jobs?search_keywords=Transformer%20serving.md)[vLLM](https://jobicy.com/jobs?search_keywords=vLLM.md)[TensorRT-LLM](https://jobicy.com/jobs?search_keywords=TensorRT-LLM.md)[Triton Inference Server](https://jobicy.com/jobs?search_keywords=Triton%20Inference%20Server.md)[Model quantization](https://jobicy.com/jobs?search_keywords=Model%20quantization.md)[KV-cache optimization](https://jobicy.com/jobs?search_keywords=KV-cache%20optimization.md)[Speculative decoding](https://jobicy.com/jobs?search_keywords=Speculative%20decoding.md)[Distributed inference](https://jobicy.com/jobs?search_keywords=Distributed%20inference.md)[GPU performance optimization](https://jobicy.com/jobs?search_keywords=GPU%20performance%20optimization.md)[Benchmarking](https://jobicy.com/jobs?search_keywords=Benchmarking.md)[Request routing](https://jobicy.com/jobs?search_keywords=Request%20routing.md)[NCCL](https://jobicy.com/jobs?search_keywords=NCCL.md) Sample interview questionsHow would you diagnose a regression in p99 latency after deploying a new LLM serving configuration?I would first reproduce the regression with representative traffic and a controlled benchmark harness, then compare TTFT, TPOT, queue time, GPU utilization, memory use, cache hit rate, and error rates against the prior configuration. I would trace the request path across gateway, scheduler, runtime, kernels, and cluster layers, isolate the changed variable, and validate a rollback or targeted fix through a staged rollout. What trade-offs do you consider when selecting a quantization approach for production inference? I evaluate model quality, memory savings, throughput, latency, hardware support, implementation complexity, and operational reliability. I would benchmark alternatives such as FP8, INT8, INT4, AWQ, or GPTQ on representative workloads, including long-context and concurrency cases, and choose the lowest-cost configuration that meets agreed quality and reliability thresholds. When can prefill-decode disaggregation improve LLM serving performance? It can help when prefill and decode have materially different compute, memory, or scheduling profiles and separating them improves utilization or reduces tail latency. I would assess KV-cache transfer overhead, network topology, workload mix, worker placement, queueing behavior, and capacity balance before adopting it, because the extra communication can outweigh benefits for some traffic patterns. How would you tune parallelism for multi-node mixture-of-experts inference? I would profile expert routing balance, communication volume, memory limits, interconnect bandwidth, and end-to-end latency under realistic batch sizes. Based on those measurements, I would tune tensor, pipeline, data, and expert parallelism while accounting for topology-aware placement and WideEP trade-offs, then validate the configuration with reproducible throughput and p99 latency tests. How do you ensure that an inference optimization preserves model quality in production? I define quality metrics and acceptance thresholds before implementation, then test against curated offline evaluations, representative prompts, structured-output cases, and regression suites. I would release through canary or shadow traffic where possible, monitor quality and reliability signals alongside performance metrics, and maintain a rapid rollback plan. Opportunity details ## About this role. 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. ### The role As a Senior Machine Learning Engineer on the 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, and benchmarking to improve latency, throughput, memory efficiency, GPU utilization, and cost per token while preserving quality and reliability. You will work with kernel and platform engineers to investigate serving problems, compare configurations, and resolve performance and quality regressions. 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 through reproducible benchmarks and safe production rollouts under real-world workloads. ### Your responsibilities * Own optimization projects for specific model families, customer endpoints, or serving backends. * Compare inference engines and recommend serving configurations suited to individual workloads. * Diagnose model-quality and performance regressions during production rollouts. * Improve LLM and VLM endpoint latency, throughput, memory efficiency, GPU utilization, quality, and cost per token. * Deploy, configure, benchmark, and extend engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, and NVIDIA Dynamo. * Develop production model-compression workflows covering quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery. * Implement 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. * Design 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. * Scale 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. * Build reproducible benchmark harnesses measuring TTFT, 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. * Collaborate with GPU kernel and platform engineers to trace bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. * Produce design documents, performance reports, rollout plans, and customer-facing technical explanations. ### Must-haves * Strong engineering skills in Python and PyTorch. * Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference. * Practical knowledge of at least one modern inference stack, such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or an equivalent internal system. * A strong understanding of transformer inference bottlenecks involving KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. * Ability to quantify trade-offs among latency, throughput, quality, utilization, and cost. * Experience 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. * Strong communication and collaboration skills across research, kernel, infrastructure, product, and customer teams. ### Nice-to-haves * Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, or SmoothQuant. * Experience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or related inference acceleration methods. * Experience supporting agentic workloads involving tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. * Familiarity with CUDA or Triton; the role does not require kernel engineering to be the candidate’s primary specialization. * Contributions to open-source projects such as vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, or KServe. * Implementation experience with cache-aware request routing, PDD, or WideEP, including diagnosing communication bottlenecks and load imbalance. * Familiarity with GPU communication libraries and interconnects, such as NCCL, NVLink, InfiniBand, or RoCE. Benefits & Perks: * Competitive compensation * Career growth and learning opportunities * Flexibility and ownership * Collaborative and innovative culture * Opportunity to work on impactful AI projects * International environment and talented teams 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. Show more [Apply now >](https://jobicy.com/jobs/157431-senior-machine-learning-engineer-llm-inference-optimization.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![Vonage logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/1bac058d-221.jpg) Vonage Oct 27 New ### [Staff Software Engineer](https://jobicy.com/jobs/157425-staff-software-engineer-12.md) Join Vonage and help us innovate cloud communications for businesses worldwide! About Vonage Vonage is the emerging leader in the $100B+ cloud communications platform (CPaaS) market. Customers like Airbnb, Viber,… * ![Grafana Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/11/42a3c42246467ec231dd876e92b63452.jpeg) Grafana Labs Oct 27 New ### [Senior Engineering Manager, Grafana Frontend | Germany | Remote](https://jobicy.com/jobs/157408-senior-engineering-manager-grafana-frontend-germany-remote.md) Grafana Labs is the company behind Grafana Cloud, the fully managed observability platform trusted by more than 10,000 organizations to ensure reliability, resolve incidents faster, and optimize telemetry at scale…. * ![Canonical logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b4d068a9-221-1.png) Canonical Oct 27 New ### [Engineering Manager – Ubuntu Core](https://jobicy.com/jobs/157405-engineering-manager-ubuntu-core.md) Canonical is a leading provider of open source software and operating systems to the global enterprise and technology markets. Our platform, Ubuntu, is very widely used in breakthrough enterprise initiatives… * ![Mozilla logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/10/mozilla.jpg) Mozilla Oct 27 New ### [Senior Contract C++ / JavaScript Software Engineer (Browser Engine)](https://jobicy.com/jobs/157389-senior-contract-c-javascript-software-engineer-browser-engine.md) The role You will help the Firefox DOM Core team improve the health of the Session History area. You will write tests to improve the coverage; you will fix tests… * ![Veracyte logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/08/1917a215-221.jpeg) Veracyte Oct 27 New ### [Software Development Manager](https://jobicy.com/jobs/157382-software-development-manager-2.md) At Veracyte, we offer exciting career opportunities for those interested in joining a pioneering team that is committed to transforming cancer care for patients across the globe. Working at Veracyte… * ![Socket logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/1314ce3c-221.png) Socket Oct 27 New ### [Engineering Manager](https://jobicy.com/jobs/157378-engineering-manager-14.md) About Us Socket helps devs and security teams ship faster by cutting out security busywork. Thousands of orgs use Socket to safely find, audit, and manage open source code. Our… * ![Mozilla logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/10/mozilla.jpg) Mozilla Oct 27 New ### [Contract Staff Software Engineer – WebCompat & Bug Triage](https://jobicy.com/jobs/157376-contract-staff-software-engineer-webcompat-bug-triage.md) You will help reduce Firefox’s WebCompat bug backlog by finishing or verifying the diagnosis of the long tail of site-breakage bugs, and by writing interventions or simple fixes (often with… * ![Customer.io logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b82146da-221.jpg) Customer.io Oct 27 New ### [GTM AI Engineer](https://jobicy.com/jobs/157343-gtm-ai-engineer.md) About Customer.io Over 9,000 companies — from scrappy startups to global brands — use our platform to send billions of emails, push notifications, in-app messages, and SMS every day. Customer.io… * ![Customer.io logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b82146da-221.jpg) Customer.io Oct 27 New ### [Engineering Manager](https://jobicy.com/jobs/157337-engineering-manager-13.md) Hi, I’m Paul, VP of Engineering at Customer.io. We’re always looking for thoughtful, driven Engineering Managers to add to our org. Some of our teams are building customer-facing product and… * ![Applied Intuition logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/8726d2bf-221.png) Applied Intuition Oct 27 New ### [Field Integration Engineer](https://jobicy.com/jobs/157314-field-integration-engineer.md) Applied Intuition, Inc. is powering the future of physical AI. Founded in 2017 and now valued at $15 billion, the Silicon Valley company is creating the digital infrastructure needed to… [Browse all jobs](https://jobicy.com/jobs.md)