Senior AI Researcher- Reinforcement learning (f/m/d)
Core
Shape and improve reinforcement learning methodology for large-scale LLM training to enhance model capabilities for customers.
Role type
Senior AI Researcher (Reinforcement Learning)
Builds
Large-scale LLM training runs and improved RL models
Domain
Artificial Intelligence / Reinforcement Learning / Large Language Models
Deliverable
production ML models
Required skills
Reinforcement Learning theory, multi-node LLM training, distributed algorithms, Python, ML tooling (PyTorch distributed), statistical evaluation methods
Preferred skills
PhD in RL, publications in top-tier venues (NeurIPS, ICML, ICLR), LLM evaluation and environment crafting
Technologies
PyTorch distributed
Responsibilities
Conduct large-scale LLM training runs and analyze evaluation scores, identify and implement novel approaches to multi-turn reinforcement learning, optimize RL training loops for large-scale training, partner with post-training teams to turn feedback into actionable training signals
Seniority
Senior, hands-on IC