jobs

Agent Post-Training, Context 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

2026-06-26T17:42:27.891+00:00

OpenAI is hiring a Context Researcher for the Agent Post-Training team in San Francisco, on-site. The work centers on scaling compute spent on context: designing experiments, owning post-training stack improvements across RL, data pipelines, graders, reward signals and evals, and turning model failures into training data or product fixes. The posting asks for strong ML or software fundamentals and hands-on experience with LLMs, RLHF/RLAIF, post-training or production ML systems. Distinctive: a stated product interface (Codex Chronicle) for iterative deployment, and close work with Codex and ChatGPT teams.