Research Engineer / Scientist - Reinforcement Learning

Highlights

• Develop RL methods for reasoning, coding, and long-horizon tasks.
• Design experiments on how RL scales with size, compute, and horizon.
• Turn experimental findings into training recipes for larger models.

What they offer

• Equity incentives
• Flexible work arrangements with remote or in-person options in San Francisco
• Visa sponsorship and relocation assistance
• Quarterly team off-sites, hackathons, conferences and learning opportunities

Ideal candidate

A curious RL researcher or engineer who loves running controlled experiments, debugging unstable training, and turning insights into robust recipes to advance open frontier models.

Requirements

• Demonstrated depth in RL algorithms, empirical research on model training, or distributed ML systems
• Strong programming skills in Python and experience with PyTorch or comparable ML framework
• Ability to design controlled experiments, interpret results, and debug model or system behavior
• Experience taking research ideas or systems changes through implementation, testing, and evaluation