Applied Researcher - Agentic RL

The role

You will work on reinforcement learning for agents that reason over long horizons, use tools, coordinate with other agents, recover from failure, and improve from experience. This role focuses on RL and ML systems across algorithms, environments, harnesses, reward and credit-assignment methods, evaluation, and scalable experimental systems.

What you will do

• Turn workflows into tasks, environments, evaluations, and reward signals
• Run post-training experiments against real baselines and deploy what works
• Work directly with customers, users, or research partners
• Build agentic judges and credit-assignment methods
• Make multi-agent and long-horizon environments train reliably at scale
• Detect when gains come from reward hacking, harness behavior, data leakage, or infrastructure artifacts
• Own RL and post-training methods for tool-using, multi-agent, memory-augmented, and long-horizon systems
• Develop reusable environments, harnesses, rewards, and evaluations
• Conduct experiments connecting algorithm choices to training and inference behavior
• Build open-source systems and papers

Required qualifications

• Hands-on RL training, scalable ML systems, agent environments, evaluation, inference/training infrastructure, or research crossing methods and systems
• Hands-on experience building and debugging model-training, post-training, agent, evaluation, or closely adjacent experimental loops
• Strong experimental judgment
• Strong Python
• Ability to build artifacts that other researchers and engineers can run, inspect, and extend
• Comfort owning ambiguous problems

Nice to have

• Publications
• Open-source systems
• Benchmarks
• Shipped products

Benefits

• Cash Compensation Range of $150-300k + equity incentives
• Flexible Work (San Francisco, New York, London, or remote)
• Visa Sponsorship & relocation support
• Professional Development budget
• Team Off-sites & conference attendance

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.