Agent Post-Training, Personality

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, and successful outcomes
• Work with human experts and trainers to produce high-quality preference data and tasteful rollouts
• Improve reward models and RL objectives for model behaviors
• Work with pretraining and early-training teams on data mixtures, objectives, and synthetic data
• Build sustainable pipelines for updating training data as understanding of model behavior evolves
• Partner with ChatGPT, Codex, and other product teams to turn consumer insight into model improvements

Requirements

• Strong technical foundations in machine learning, software engineering, statistics, behavioral science, or HCI
• Experience with LLMs, post-training, RL/RLHF, reward modeling, evals, or production ML systems
• Ability to translate subjective product questions into falsifiable hypotheses and rigorous evaluations
• Strong taste for model behavior and ability to explain qualitative differences in model responses
• Ability to work effectively with researchers, engineers, product teams, and designers

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.