Senior LLM Inference Scientist

FDE Times; Greater London; Hybrid; GBP 110,000 - 180,000; Full time

Benefits offered by this job

Competitive pay

Career growth

Flexibility and ownership

Collaborative culture

Impactful AI projects

International team

Job summary

Nebius is hiring for a research-focused role in their cloud AI platform. You will own focused research on efficient LLM and VLM inference, conduct rigorous experiments, and translate findings into production capabilities.

Your work will span quantization, distillation, speculative decoding, and model/runtime co-optimization, influencing end-to-end system design. You will collaborate with engineers to build prototypes, evaluate latency, throughput, and cost per token, and publish results through

Qualifications

• PhD in computer science, ML, ML systems or related field.
• Strong publication record or equivalent artifacts in ML/efficient inference/ model compression.
• Strong Python and PyTorch implementation skills.

Responsibilities

• Lead research projects in efficient LLM and VLM inference, from hypotheses to production handoff.
• Develop and evaluate methods spanning quantization, QAT, distillation, and co-optimization.
• Build prototypes using PyTorch, Triton, CUDA-adjacent tooling, and inference-serving frameworks.

Skills

Python

PyTorch

LLMs

VLMs

research

Education

PhD in CS/ML or related

Tools

PyTorch

CUDA

Triton

TensorRT

Job description

Nebius is hiring for a research-focused role in their cloud AI platform. You will own focused research on efficient LLM and VLM inference, conduct rigorous experiments, and translate findings into production capabilities.

Your work will span quantization, distillation, speculative decoding, and model/runtime co-optimization, influencing end-to-end system design. You will collaborate with engineers to build prototypes, evaluate latency, throughput, and cost per token, and publish results through