jobs
Research Engineer/Research Scientist-Post Training
About the Team The Post-Training team advances OpenAI’s frontier models and prepares them for deployment in ChatGPT, Codex, the API, and future products. We work at the intersection of research and…
In inglese
- Company
- OpenAI
- Location
- San Francisco
- Status
- Open
- Posted
- 2026-06-25 00:25 UTC
OpenAI's Agent Post-Training team is hiring a researcher to improve the capabilities and reliability of its agentic models. The work spans RL, data pipelines, graders, reward signals, evals, diagnostics, and early-training interventions such as data mixtures and synthetic data. The posting asks for hands-on experience with LLMs, post-training, RLHF/RLAIF, or tool-using agents, and comfort with ambiguous problems across research and engineering. It is deliberately broad, names no fixed subfield, and may be based in San Francisco or London.
Original job posting