Agent: Post-Training Personality for Trusted AI

OpenAI; San Francisco (CA); On-site; USD 380,000 - 500,000; Full time

Job summary

OpenAI in San Francisco seeks an Agent Post-Training, Personality to help shape how agents collaborate with users and other products. You will study what makes agents thoughtful, proactive, and easy to work with, then translate those insights into evals, training data, reward signals, and model improvements.

You will collaborate with product teams, researchers, and trainers to ensure improvements survive the full training stack and reach products used daily by Developers, enterprises, and

Responsibilities

• Develop a rigorous understanding of what makes an agent a great collaborator across professional, creative, technical, and everyday work.
• Turn qualitative judgments about model behavior into concrete hypotheses, evals, graders, and training interventions.
• Study explicit and implicit user signals to understand which behaviors create trust, satisfaction, continued use, and successful outcomes.
• Work with human experts and trainers to produce high-quality, tasteful rollouts and preference data that capture excellent collaborative behavior.
• Improve reward models and RL objectives for model behaviors.
• Work with pretraining and early-training teams on data mixtures, objectives, synthetic data, and other upstream choices that shape downstream personality.
• Build sustainable pipelines for updating older training data as our understanding of excellent model behavior evolves.
• Partner closely with ChatGPT, Codex, and other product teams to turn consumer insight into model improvements and validate them in real workflows.
• Own projects end to end, from observing a subtle behavioral failure through experimentation, training, evaluation, and launch.

Job description

OpenAI in San Francisco seeks an Agent Post-Training, Personality to help shape how agents collaborate with users and other products. You will study what makes agents thoughtful, proactive, and easy to work with, then translate those insights into evals, training data, reward signals, and model improvements.

You will collaborate with product teams, researchers, and trainers to ensure improvements survive the full training stack and reach products used daily by Developers, enterprises, and