Researcher, 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 and tasteful rollouts that capture excellent collaborative behavior.
• Partner with pretraining and product teams to integrate personality improvements into the full training stack and real-world 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.
• Proven experience with Large Language Models (LLMs) and post-training methodologies.
• Hands-on experience with RL/RLHF, reward modeling, and creating robust evaluations.
• Experience working with synthetic data and production ML systems.
• Ability to translate subjective product questions into falsifiable hypotheses and rigorous technical experiments.
• Strong communication skills to collaborate effectively with researchers, engineers, and designers.

Preferred Qualifications

• Background in behavioral science or Human-Computer Interaction (HCI).
• Deep "taste" for model behavior and the ability to articulate why specific model responses feel natural or useful.
• Experience managing end-to-end projects from behavioral observation through to training and launch.

Benefits

• Competitive base salary and generous equity packages.
• Comprehensive medical, dental, and vision insurance.
• 401(k) retirement plan with employer match.
• Flexible paid time off 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 products like ChatGPT and the API.