jobs

Agent Post-Training, Connectors 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

2026-06-26T17:42:35.498+00:00

OpenAI's Agent Post-Training team is hiring in San Francisco for its Connectors group, which teaches agents to work with professional software through code. The person will design experiments and improve the post-training stack, including RL, data pipelines, graders, reward signals and evals, so models can act across Slack, Google Workspace, GitHub, Notion, Linear and Salesforce. The posting asks for technical strength in machine learning or software engineering and hands-on experience with LLMs, RLHF/RLAIF, post-training or tool-using agents, plus work alongside product, infrastructure and safety teams.