Senior AI Researcher- Reinforcement learning(m/w/x)

Requirements

• Deep understanding of Reinforcement Learning theory
• Experience with multi-node LLM training
• Familiarity with statistical evaluation methods
• Ability to analyze evaluation environments
• Strong Python and ML tooling skills
• Willingness to relocate or travel
• PhD in RL or equivalent research
• Contributions to top-tier RL venues
• Experience evaluating LLM models

Tasks

• Shape and improve underlying RL methodology
• Maintain a high-quality training code-base
• Conduct large-scale reinforcement learning experiments
• Derive hypotheses from experimental results
• Iterate on implementation and methodology
• Execute large-scale LLM training runs
• Analyze evaluation scores in depth
• Propose and implement performance improvements
• Maximize performance on internal benchmarks
• Identify and implement novel multi-turn RL approaches
• Stay current with bleeding-edge RL research
• Identify and resolve training infrastructure bottlenecks
• Optimize RL loops for large-scale training
• Partner with post-training teams on feedback
• Convert raw feedback into actionable training signals
• Ensure RL iterations improve downstream performance

Work Experience

Education

Languages

Tools & Technologies