Global AI MapJOBS / H Company
Research Engineer / Scientist, Post-training & Reinforcement Learning - London
Hybrid London
Role
The role involves developing and training advanced LLMs and VLMs for agentic AI applications, focusing on post-training and reinforcement learning techniques. Candidates must have strong programming skills in Python or Rust, proficiency in deep learning frameworks, and experience with distributed training and RL methods.
Location: Hybrid London
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: 2026-04-14T10:00:56.803+00:00. Check the employer’s page for the complete description, current availability and application terms.