jobs
Researcher, Synthetic RL
OpenAI’s Synthetic RL team develops reinforcement learning methods that use synthetic data, environments, and feedback to train and evaluate frontier AI models.
- Company
- OpenAI
- Location
- San Francisco, United States
- Status
- Closed
- Posted
- 2026-10-23 03:33 UTC
A research role on OpenAI's Synthetic RL team, which builds reinforcement learning methods using synthetic data, environments, and feedback to train and evaluate frontier models. The researcher develops RL techniques, designs and runs experiments on training dynamics and model behavior at scale, analyzes results, and works with researchers and engineers to fold successful approaches into model-training pipelines. The posting asks for a strong reinforcement learning or ML research background plus engineering and statistical analysis skills, and comfort with fast iteration in uncertain problem spaces. Based in San Francisco with three office days weekly; relocation assistance offered.
Original job posting