Applied Researcher in Reinforcement Learning

Job Summary

Focusing on reinforcement learning for agents that reason over long horizons, the full-time Applied Researcher in Reinforcement Learning will develop scalable systems and methods while collaborating with application teams and open-source users, with the flexibility to work remotely or from major cities like San Francisco, London, or New York.

Key responsibilities

• Develop RL and post-training methods for tool-using, multi-agent, memory-augmented, and long-horizon systems
• Create reusable environments, harnesses, rewards, and evaluations for reinforcement learning applications
• Conduct experiments connecting algorithm choices to training and inference behavior, while extending existing research initiatives

Required qualifications

• Hands-on experience with RL training, scalable ML systems, and agent environments
• Proven ability to build and debug model-training and evaluation loops
• Strong experimental judgment and the capability to adapt based on evidence
• Proficiency in Python and experience creating artifacts for research and engineering use
• Comfort in managing ambiguous problems and maintaining communication with partners and teammates