SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 350,000 / annual
Prime Intellect is building an open superintelligence stack—infrastructure that frontier AI labs typically build internally, now made available to every ambitious AI team. The company's platform, Lab, unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment into a full-stack system for post-training at frontier scale, from supervised fine-tuning and reinforcement learning to tool use, agent workflows, and continuously improving production models.
You will help develop the algorithms and systems used to train Prime Intellect's open models with reinforcement learning. The role spans three focus areas (you'll specialize based on your strengths):
**Algorithm Research:** 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. Collaborate with data and evaluation researchers to understand how task selection, rewards, and training data affect model learning.
**Scaling Science:** 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. Convert experimental findings into training recipes and test whether improvements hold across larger models and longer runs.
**RL Frameworks:** Extend prime-rl (https://github.com/PrimeIntellect-ai/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.
Prime Intellect has raised $150M in total funding from Founders Fund, Radical Ventures, NVIDIA, and exceptional AI, infrastructure, and enterprise operators including Andrej Karpathy, Dwarkesh Patel, and leaders from Ramp, Perplexity, Harvey, Mercor, Zapier, Datadog, Cognition, OpenAI, and many others.
**Requirements:**
- Demonstrated depth in at least one of: RL algorithms, empirical research on model training, or distributed ML systems (through research, open-source contributions, or systems you've built)
- Strong programming skills in Python and experience with PyTorch or 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 clear accounting of what worked and what didn't
**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
