Skip to content
AI.info

jobs

Research Engineer, Frontier Evals & Environments

About the team The 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…

Company
OpenAI
Location
San Francisco
Status
Closed
Posted
2025-04-13 17:25 UTC

Research engineer on OpenAI's Agent Post-Training team, building evaluation environments and benchmarks that steer the company's largest training runs. Work includes designing reinforcement-learning environments, methods that automatically probe model behavior, measurement research on reliability and variance, and scalable evaluation systems. Public benchmarks from this kind of role include SWE-bench Verified, MLE-bench and PaperBench. The posting asks for grounding in machine learning, software engineering, systems or statistics, plus hands-on experience with LLMs, post-training, evals or agents. San Francisco, on-site.

Original job posting