Nebius предлагает четко очерченную исследовательскую роль на стыке быстрорастущего AI-инфраструктурного рынка и разработки для продакшена. Современный стек и понятная связь исследований с внедрением выглядят привлекательно, но без диапазона зарплаты сложно оценить условия.
?Зарплата не указана
Современный стек
Понятные задачи
AI-инфраструктура
От исследований к продакшену
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Applied Scientist (Efficient LLM Inference): Developing and productionizing efficient LLM and VLM inference methods with an accent on quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization. Focus on designing rigorous experiments, building PyTorch and Triton prototypes, measuring quality and system performance, and transferring research into production inference components.
Location: Amsterdam, Netherlands; Berlin, Germany; London, United Kingdom; Poland; Prague, Czech Republic; Tel Aviv, Israel; or Zurich, Switzerland. Applicants must be authorized to work in the country where they apply.
Company
Nebius builds a full-stack AI cloud platform for data processing, model training, and production deployment, with infrastructure spanning compute, storage, networking, and applied AI.
What you will do
Own research projects from hypothesis and experiment design through ablation, prototyping, and production handoff.
Define and execute research programs in efficient LLM and VLM inference with measurable production impact.
Develop and productionize methods for quantization, QAT, distillation, speculative decoding, KV-cache reuse and compression, long-context inference, MoE routing, and model/runtime co-optimization.
Build prototypes with PyTorch, Triton, CUDA-adjacent tooling, and inference-serving frameworks.
Evaluate quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token.
Collaborate with MLE, GPU kernel, backend infrastructure, product, and customer teams; publish technical work and mentor engineers and scientists.
Requirements
PhD in computer science, machine learning, ML systems, computer systems, computer architecture, electrical engineering, applied mathematics, or a related field.
Strong publication record or equivalent research artifacts in ML, ML systems, efficient inference, model compression, quantization, distillation, or serving systems.
Strong hands-on coding skills in Python and PyTorch.
Deep understanding of LLMs, VLMs, transformer inference, decoding algorithms, model compression, quantization, and production-serving tradeoffs.
First-author publications in leading ML, systems, architecture, or NLP venues.
Experience deploying ML models or inference optimizations in production.
Experience with vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, FlashAttention, FlashInfer, Triton, CUDA, or PyTorch internals.
Experience with post-training, SFT, DPO, RLHF, RLAIF, preference optimization, or synthetic data generation related to inference quality or efficiency.
Open-source research artifacts, widely used benchmarks, technical blogs, or invited talks in efficient AI systems.
Culture & Benefits
Competitive compensation.
Career growth and learning opportunities.
Flexibility and ownership.
Collaborative, innovative, and international working environment.
Opportunity to work on impactful AI projects.
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 →