AI Research Scientist, Reinforcement Learning (LLM) and Post-Training
Summary
Research scientist developing reinforcement learning methods for post-training large language models and code models. Day-to-day work includes designing reward models and training curricula, running on/off-policy RL experiments, scaling RL infrastructure, and publishing at top academic venues.
- Analyze failure modes reward hacking and instability
- Collaborate to scale training with RL infrastructure
- Define interfaces for rollout generation and logging
- Design reward models and training curricula
- Develop reinforcement learning methods for post training large language models and code models
- Publish research at top academic venues
- Run off policy and on policy training experiments