jobs

Agent Post-Training, Personality

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

2026-06-26T17:42:19.579+00:00

OpenAI's Agent Post-Training team is hiring for its Personality group in San Francisco, on-site, full time. The person studies what makes an agent a good collaborator — judgment, proactivity, honesty, adaptation — and turns that into evals, graders, training data, reward models and RL objectives. The posting asks for technical foundations in machine learning, software engineering, statistics, behavioral science or HCI, plus experience with LLMs, post-training, RLHF, reward modeling or production ML. Distinctive: subjective-sounding behavior questions treated as falsifiable experiments, and work spanning pretraining through shipped products.