Agent Post-Training, Personality

Responsibilities

• Develop a rigorous understanding of what makes an agent a great collaborator across professional, creative, and technical domains.
• Translate qualitative judgments about model behavior into concrete hypotheses, evaluations, graders, and training interventions.
• Improve reward models and RL objectives to shape model behaviors and personality.
• Work with human experts to produce high-quality preference data that captures excellent collaborative behavior.
• Partner with product teams (ChatGPT, Codex) to turn consumer insights into model improvements and validate them in real workflows.
• Build sustainable pipelines for updating training data as understanding of model behavior evolves.

Requirements

• Strong technical foundations in machine learning, software engineering, or statistics.
• Experience with Large Language Models (LLMs).
• Experience with Reinforcement Learning from Human Feedback (RLHF) and reward modeling.
• Background in behavioral science, Human-Computer Interaction (HCI), or a related field.
• Ability to translate subjective product questions into rigorous, falsifiable evaluations.

Preferred Qualifications

• Experience with synthetic data generation and pretraining data mixtures.
• Experience working with production ML systems.
• Strong "taste" for model behavior and the ability to articulate why specific responses feel natural or useful.

Benefits

• Competitive base salary and generous equity.
• Comprehensive medical, dental, and vision insurance.
• 401(k) retirement plan with employer match.
• Flexible Paid Time Off (PTO) and paid parental leave.
• Daily meals in the office and mental health support.
• Annual learning and development stipend.

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of AI capabilities and seek to safely deploy them to the world through our frontier products.