Agent Post-Training, Personality

Details

The Agent Post-Training team creates frontier agents for Codex, ChatGPT, the API, and other products. The team develops the data, environments, graders, training methods, and feedback loops that shape agent capabilities and behavior, including coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste.

The Agent Post-Training Personality team focuses on making OpenAI's agents exceptional collaborators. This includes understanding what makes an agent thoughtful, clear, perceptive, appropriately proactive, adaptable, honest during disagreement, and easy to work with. The work combines behavioral research, product thinking, research, and communication judgment, with collaboration across product, post-training, pretraining, human-data, and research teams.

Responsibilities

• Develop a rigorous understanding of what makes an agent a great collaborator across professional, creative, technical, and everyday work.
• Translate qualitative judgments about model behavior into concrete hypotheses, evaluations, 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 rollouts and preference data that capture excellent collaborative behavior.
• Improve reward models and reinforcement-learning objectives for model behaviors.
• Collaborate 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 understanding of excellent model behavior evolves.
• Partner 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 behavioral failures through experimentation, training, evaluation, and launch.

Requirements

• Strong user perspective and deep interest in how models feel to work with, beyond benchmark performance.
• Ability to translate subjective product questions into falsifiable hypotheses and rigorous evaluations while preserving important nuance.
• Interest in preserving individuality, adaptability, and behavioral diversity rather than optimizing models toward one narrow style.
• Strong technical foundations in machine learning, software engineering, statistics, behavioral science, HCI, or a related field.
• Strong judgment regarding model behavior and the ability to explain why one response is thoughtful, natural, and useful while another is not.
• Experience with LLMs, post-training, reinforcement learning, RLHF, reward modeling, evaluations, synthetic data, pretraining data, or production machine-learning systems.
• Comfort working on ambiguous capability problems involving noisy signals and qualitative failures, where solutions may involve data, training, evaluations, product changes, or a combination of these.
• Ability to collaborate with researchers, engineers, product teams, designers, domain experts, human-data teams, and safety teams.
• Clear communication skills and willingness to build durable systems and processes.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. The company is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities. Background checks are administered in accordance with applicable law.

Benefits

• Base salary of $295,000–$445,000 USD, plus equity and performance-related bonuses for eligible employees.
• Medical, dental, and vision insurance, with employer contributions to Health Savings Accounts.
• Pre-tax accounts for health, dependent care, and commuter expenses.
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off, company holidays, office closures, and paid sick or safe time as applicable.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Additional taxable fringe benefits, including charitable donation matching and wellness stipends.