Research Scientist, Scaling RL

Highlights

• Train frontier models to develop deep scientific reasoning for tasks.
• Study how RL performance scales with compute, model size and data.
• Take ideas from controlled experiments to largest runs like Periodic Neon.

What they offer

• Equity

Ideal candidate

Experienced RL researcher with 5+ years training LLMs who loves rigorous experimentation and scaling small insights to frontier runs. Detail-oriented builder comfortable debugging complex stacks to advance scientific reasoning.

Requirements

• Hands-on experience training LLMs with reinforcement learning
• Strong attention to detail and rigorous approach to answer questions scientifically
• Experience with small-scale RL setups that transfer to large-scale training runs
• Comfort working across a complex training stack to implement, debug and test new research ideas
• Minimum experience: 5+ years
• Minimum education: Bachelor's degree or similar experience