Global AI MapJOBS / Luma AI
Research Scientist / Engineer – Reinforcement Learning Infrastructure
London, UK; Remote, UK
Role
The role involves designing and scaling distributed reinforcement learning systems for post-training LLMs across thousands of GPUs. Candidates must have hands-on experience with RL post-training, distributed PyTorch, and building RL environments or reward infrastructure.
Location: London, UK; Remote, UK
Employment: unspecified
Work pattern: hybrid
Seniority: unspecified
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2026-10-08T16:50:21.689+00:00. Check the employer’s page for the complete description, current availability and application terms.