jobs

Research Engineer/Research Scientist, RL/Reasoning

About the TeamThe RL and Reasoning team drives the core reasoning paradigm and has created groundbreaking innovations such as o1 and o3. They focus on pushing the boundaries of reinforcement learning research, building next-generation gener

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2025-05-14T23:26:30.369+00:00

OpenAI's RL and Reasoning team, which produced o1 and o3, is hiring a research engineer or research scientist to advance reinforcement learning methods for training aligned, general-purpose agents and next-generation generative models. The work covers RL research, running controlled experiments, and debugging and improving a large ML codebase. The posting asks for a background in reinforcement learning research, strong coding, fast iteration, and deep machine-learning knowledge. It is based in San Francisco on a hybrid schedule of three office days a week, with relocation assistance offered.