Research Engineer / Scientist - Reinforcement Learning

The role

This person will develop algorithms and systems used to train open models with reinforcement learning. Work includes algorithm research, scaling science, and extending RL frameworks.

What you will do

• Develop and test RL methods for reasoning, coding, and long-horizon tasks
• Investigate stability in asynchronous RL
• Work with data and evaluation researchers
• Design experiments to understand how RL performance and learning dynamics change
• Use controlled ablations and evaluations to distinguish learning gains
• Turn experimental findings into training recipes
• Extend prime-rl to support new algorithms, models, and asynchronous training workflows
• Improve performance and numerical correctness of research runs
• Build diagnostics to reproduce unstable runs and performance regressions

Required qualifications

• Demonstrated depth in at least one of RL algorithms, empirical research on model training, or distributed ML systems
• Strong programming skills in Python
• Experience with PyTorch or a comparable ML framework
• Ability to design controlled experiments, interpret results, and debug unexpected model or system behavior
• Experience taking a research idea or systems change through implementation, testing, and evaluation

Nice to have

• Experience with distributed training frameworks or asynchronous rollout pipelines
• Experience diagnosing unstable RL runs, including policy-staleness or numerical issues
• Work on coding agents, verifiable rewards, or long-horizon environments

Benefits

• Cash Compensation Range of $150-350k, including equity incentives
• Flexible work arrangements, with the option to work remotely or in-person at our offices in San Francisco
• Visa sponsorship and relocation assistance for international candidates
• Quarterly team off-sites, hackathons, conferences and learning opportunities
• Opportunity to work with a talented, hard-working and mission-driven team

About the company

Prime Intellect is building the open superintelligence stack. The platform, Lab, unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into one full-stack system.