jobs

Agent Post-Training Research

About the TeamThe 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 products: persistent, proactive intelligence that

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-06-25T00:25:42.611+00:00

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.