jobs

Researcher, Synthetic RL

About the TeamThe Synthetic RL team develops reinforcement learning methods that leverage synthetic data, environments, and feedback to train and evaluate frontier AI models. The team explores approaches such as self-play, simulators, and o

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-01-09T21:12:59.003+00:00

OpenAI's Synthetic RL team is hiring a research scientist to develop reinforcement learning methods that use synthetic data, environments and feedback to train and evaluate frontier models. The work covers algorithm development, experiments on training dynamics and model behavior at scale, and integrating successful approaches into production training pipelines. The posting asks for a strong background in reinforcement learning or machine learning research, plus engineering and statistical analysis skills. It is based in San Francisco under a hybrid model of three office days a week, with relocation assistance.