Agent Post-Training, Personality
OpenAI · San Francisco
CHECKED 1H AGO
Frontier labonsite$380k–$500k
At a glance
Highlights
- Shape frontier agents shipped in ChatGPT, Codex and API products.
- Turn collaboration insights into evals, reward signals and training data.
- Study user trust signals to improve long-horizon agent behavior.
Ideal candidate
Product-minded researcher with strong ML foundations and taste for model behavior who thinks from the user's perspective and thrives turning ambiguous, qualitative collaboration problems into shipped agent improvements.
Requirements
- Strong technical foundations in machine learning, software engineering, statistics, behavioral science, HCI, or related field
- Experience with LLMs, post-training, RL/RLHF, reward modeling, evals, synthetic data, or production ML systems
- Ability to translate subjective product questions into falsifiable hypotheses and rigorous evaluations
- Ability to collaborate across research, engineering, product, design and human-data teams
Lab profile
About OpenAI
Builds safe frontier AI models and products like ChatGPT for broad benefit.
What they build
- ChatGPT
- OpenAI API
- Frontier AI models
Known for
- Frontier-scale distributed ML training
- Massive GPU fleet and data center operations
- Exabyte-scale data lakes and streaming
- AI alignment and safety research
Key facts
- Operates one of the world's largest GPU fleets