Research Scientist / Engineer – Reinforcement Learning Infrastructure

Summary

Full-time role at Luma AI, Inference Compute team. RoleRadar classifies it as research. Listed locations: London, UK; Remote, UK. Skills mentioned include PyTorch, vLLM / TensorRT, Ray, LLMs, RLHF & post-training and Reinforcement learning.

Generated by RoleRadar from facts in the posting. We don't reproduce the job description; read it in full on Luma AI's job page.

Key facts

Salary

Not published by the employer

Location

• London, UK
• Remote, UK

Workplace

Hybrid

From the workplace field on the employer's job board.

Countries

United Kingdom

Inferred by RoleRadar from the listed locations.

Experience

Not stated in the posting

PhD

Not mentioned

Visa sponsorship

Not stated in the posting

Team

Research & AI · Inference Compute

Skills mentioned

• PyTorch
• vLLM / TensorRT
• Ray
• LLMs
• RLHF & post-training
• Reinforcement learning
• Distributed training
• Inference optimization