jobs

Research Engineer, Code RL (Reinforcement Learning)

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

In inglese

Company

Anthropic

Location

San Francisco, CA; New York City, NY

Status

Open

Posted

2026-06-11T21:47:04+00:00

Anthropic is hiring a Research Engineer for its Code RL team, focused on improving Claude models' software-engineering abilities. The role combines RL research and engineering: designing coding tasks and RL environments, building reward signals and verifiers, running training experiments on frontier models, and diagnosing model performance. The posting asks for strong Python and async/concurrent programming, end-to-end system ownership, and rigorous experimental design. Distinctive aspects include work on agentic coding, long-horizon autonomous engineering, and high-performance accelerator code, with collaboration across alignment and production training teams.