Applied Research - Agentic RL

Skills

About the Role

You will develop reinforcement learning and post-training methods for long-horizon agents that use tools, collaborate, recover from failures, and learn from experience. You will build reusable environments, rewards, evaluations, and experimental systems, then test and deploy methods across application domains.

Requirements

• Hands-on experience with RL training, scalable ML systems, agent environments, evaluation, inference or training infrastructure, or research spanning methods and systems.
• Experience building and debugging model-training, post-training, agent, evaluation, or adjacent experimental loops.
• Strong experimental judgment, including meaningful baselines, trace inspection, and failure attribution.
• Strong Python skills.
• Ability to build artifacts that other researchers and engineers can run, inspect, and extend.
• Ability to own ambiguous problems and keep partners and teammates informed.

Responsibilities

• Build agentic judges and credit-assignment methods for complete trajectories.
• Develop scalable multi-agent and long-horizon training environments.
• Detect reward hacking, data leakage, harness behavior, and infrastructure artifacts.
• Develop RL and post-training methods for tool-using and multi-agent systems.
• Build reusable environments, harnesses, rewards, and evaluations.
• Run experiments connecting algorithm choices to training and inference behavior.
• Create open-source systems and papers from application research problems.

Benefits

• Flexible work in San Francisco, New York, London, or remote
• Visa sponsorship
• Relocation support
• Professional development budget
• Team off-sites
• Conference attendance