jobs
Agent Post-Training, Artifacts Research
About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier…
In inglese
- Company
- OpenAI
- Location
- San Francisco
- Status
- Closed
- Posted
- 2026-06-26 17:42 UTC
OpenAI's Agent Post-Training, Artifacts team trains the models behind its agents, and this role focuses on artifacts: documents, spreadsheets, slide decks, dashboards and reports that agents produce. The person owns improvements across the post-training stack — RL, data pipelines, graders, reward signals, evals — builds environments that surface model failures, and works with product, infrastructure and safety partners on what goes into major training runs. The posting asks for machine-learning or software fundamentals plus hands-on LLM, RL or post-training experience, and an interest in product impact.
Original job posting