Research Engineer / Scientist - Reinforcement Learning

Prime Intellect • San Francisco, CA

16h • $150,000 - $350,000

About The Position

Prime Intellect is building an open superintelligence stack: infrastructure for frontier AI research made available to AI teams. Its Lab platform combines compute, environments, evaluations, secure sandboxes, high-performance training, and deployment to support post-training at frontier scale, including supervised fine-tuning, reinforcement learning, tool use, agent workflows, and continuously improving production models.

The Research Engineer / Scientist will help develop the algorithms and systems used to train Prime Intellect’s open models with reinforcement learning. The team is hiring across RL algorithms, scaling research, and training frameworks; the role’s focus will reflect the candidate’s strengths, and candidates do not need to cover all three areas. The position involves research and implementation across training objectives and policy optimization, empirical studies of model learning and scaling, and development of Prime Intellect’s RL framework and workflows.

Requirements

• Demonstrated depth in at least one of RL algorithms, empirical research on model training, or distributed ML systems, gained through research, open-source contributions, or systems built.
• 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, with a clear account of what worked and what did not.

Nice To Haves

• 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.

Responsibilities

• Develop and test RL methods for reasoning, coding, and long-horizon tasks, including changes to training objectives and policy optimization.
• Investigate stability in asynchronous RL, including policy staleness, trainer/sampler mismatch, and numerical differences between training and rollouts.
• Work with data and evaluation researchers to understand how task selection, rewards, and training data affect model learning.
• Design experiments to understand how RL performance and learning dynamics change with model size, training compute, and task horizon.
• Use controlled ablations and evaluations to distinguish learning gains from reward exploitation, evaluation artifacts, or training bugs.
• Turn experimental findings into training recipes and test whether improvements hold across larger models and longer runs.
• Extend prime-rl to support new algorithms, models, and asynchronous training workflows.
• Improve the performance and numerical correctness of research runs across trainers, rollout workers, and environments, working with the infrastructure team.
• Build diagnostics that make unstable runs and performance regressions easier to reproduce and help distinguish algorithm problems from implementation or runtime issues.

Benefits

• Cash compensation range of $150,000–$350,000, including equity incentives.
• Flexible work arrangements, with the option to work remotely or in person at 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, mission-driven team focused on leveraging technology to accelerate science and AI.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed