jobs

Agent Post-Training, API & Power Users

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

2026-06-26T17:42:14.347+00:00

OpenAI's Agent Post-Training team is hiring for its API & power-users group in San Francisco. The role improves agentic models used by API developers and expert users. Work includes designing evals and graders, building training environments, turning developer-workflow failures into post-training data, running experiments, and carrying behavior improvements into major model runs. Candidates should have ML or software fundamentals and hands-on experience with LLMs, post-training, RL/RLHF/RLAIF, evals, synthetic data, coding or tool-using agents, or production ML systems. The posting says the role is broad and cross-functional.