Summary

Research scientist intern (phd) for the models team in london. The role focuses on training techniques for agentic ai, including post-training and reinforcement learning, reward modeling, and work across llms and vision-language models.

Responsibilities

• Develop post-training and reinforcement learning methods
• Improve instruction following for agent applications
• Work on tool use and interaction in environments
• Build self-verification and learning from feedback
• Create synthetic data generation pipelines
• Research efficient reasoning and world modeling