jobs

Agent Post-Training, Frontier Evals and Environments 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

2026-06-26T17:42:23.335+00:00

OpenAI's Agent Post-Training team is hiring a researcher for Frontier Evals & Environments in San Francisco, on-site. The work involves creating RL environments and evaluation methodology for frontier agents, measuring model capabilities and behavior, and feeding results into the largest training runs. The posting asks for strong fundamentals in machine learning, software engineering or statistics, plus hands-on work with LLMs, RL, post-training, evals or coding agents. Distinctive: earlier evaluations from this role include SWE-bench Verified and MLE-bench, and the position is described as high-agency.