Высокоуровневая роль в самом горячем секторе тех-рынка с фокусом на сложные задачи оптимизации LLM и действительно передовым стеком.
?Зарплата не указана
Передовой стек
Трендовый домен
Четкие задачи
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Machine Learning Engineer (LLM Inference Optimization): Optimizing LLM and VLM model endpoints and inference engines for production AI cloud workloads with an accent on quantization, speculative decoding, KV-cache management, distributed serving, and GPU efficiency. Focus on designing request routing and scheduling, scaling inference across multi-node GPU systems, and building reproducible benchmarks for latency, throughput, reliability, quality, and cost per token.
Location: London, United Kingdom. Applicants must be authorized to work in the country in which they apply and provide proof of employment eligibility.
Company
Nebius builds a full-stack AI cloud platform for data processing, model training, inference, and production deployment, with engineering hubs across Europe, the UK, North America, and Israel.
What you will do
Own optimization projects for LLM and VLM model families, customer endpoints, and serving backends.
Deploy, configure, benchmark, and extend inference engines including vLLM, SGLang, TensorRT-LLM, Triton Inference Server, and NVIDIA Dynamo.
Design request routers and scheduling policies, and scale dense and mixture-of-experts inference across multiple GPU nodes.
Build reproducible benchmarks and collaborate with kernel and platform engineers to diagnose bottlenecks and validate production rollouts.
Requirements
Strong engineering skills in Python and PyTorch.
Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference.
Practical knowledge of a modern inference stack such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, or KServe.
Strong understanding of transformer inference bottlenecks involving KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving.
Experience designing or optimizing distributed inference architectures, including request routing, distributed scheduling, prefill/decode disaggregation, multi-node inference, or expert parallelism.
Strong communication and collaboration skills across research, kernel, infrastructure, product, and customer teams.
Nice to have
Experience with quantization methods and formats including FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, or SmoothQuant.
Experience with distillation, speculative decoding, EAGLE, Medusa, or multi-token prediction.
Experience supporting agentic workloads with tool calling, structured outputs, streaming APIs, and high concurrency.
Familiarity with CUDA, Triton, NCCL, NVLink, InfiniBand, or RoCE.
Contributions to open-source inference and machine learning projects such as vLLM, SGLang, TensorRT-LLM, FlashInfer, PyTorch, Triton, Ray, or KServe.
Culture & Benefits
Competitive compensation.
Career growth and learning opportunities.
Flexibility, ownership, and an opportunity to shape AI infrastructure.
Collaborative, innovative, and international working environment.
Work on impactful AI projects with experienced engineering teams.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →