Senior AI Scientist - LLM/VLM Inference

Nebius Group; Greater London; Hybrid; GBP 120,000 - 170,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative culture

Impactful AI projects

International environment

Job summary

Nebius is hiring researchers to tackle frontier LLM and VLM inference bottlenecks, translating findings into production-ready capabilities. You will own focused projects, write code, and generate prototypes, publications, and artifacts for engineers.

Your work spans quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization, evaluating trade-offs in quality, latency, throughput, memory, and cost per token with engineering teams to productionize

Qualifications

• PhD in computer science, ML, ML systems, or related field.
• Strong publication record or equivalent research artifacts in ML, ML systems, efficient inference, model compression, quantization, distillation, serving systems, or related areas.
• Strong Python and PyTorch implementation skills, turning ideas into experiments and prototypes.
• Deep knowledge of LLMs, VLMs, transformer inference, decoding algorithms, model compression, quantization, and production serving trade-offs.
• Strong experimental design skills including ablations, baselines, metrics, statistics, and failure analysis.
• Excellent written and verbal communication.

Responsibilities

• Lead research projects in efficient LLM/VLM inference from hypotheses to production handoff.
• Develop and evaluate methods spanning quantization, QAT, distillation, speculative decoding, KV-cache reuse/ compression, and co-optimization.
• Build prototypes using PyTorch/Triton/CUDA tooling and collaborate to production components.
• Research LLM request routing, scheduling, cache-aware load balancing, and prefill–decode disaggregation to optimize latency and costs.
• Investigate multi-node inference, WideEP, expert placement, load balance, and trade-offs for scalability.
• Conduct rigorous evaluations of quality, latency, throughput, memory, stability, and cost per token.
• Collaborate with MLEs, kernel, infra, product, and customer teams to set impactful research priorities.
• Share results in reports, blogs, papers, and open-source artifacts; mentor others.

Skills

Python

PyTorch

LLMs

VLMs

Quantization

Research methods

Experimentation

Model compression

Education

PhD in Computer Science / ML / ML Systems

Tools

CUDA

Triton

NVIDIA TensorRT

PyTorch internals

Job description

Nebius is hiring researchers to tackle frontier LLM and VLM inference bottlenecks, translating findings into production-ready capabilities. You will own focused projects, write code, and generate prototypes, publications, and artifacts for engineers.

Your work spans quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization, evaluating trade-offs in quality, latency, throughput, memory, and cost per token with engineering teams to productionize