Agent Post-Training, Personality

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team builds the data, environments, graders, training methods, and feedback loops that shape what OpenAI’s next agents can do and what they are like to work with, then carries those improvements through major training runs and into products used by people every day. About the Role As a member of the Agent Post-training Personality team, you will help make OpenAI’s agents exceptional collaborators. You will study what makes an agent thoughtful, clear, perceptive, appropriately proactive, and genuinely easy to work with, then translate those insights into evals, training data, reward signals, and model improvements. We use “personality” to mean much more than writing style or general likability. It includes whether an agent understands what the user is trying to accomplish, communicates with good judgment, adapts to context, asks useful questions, handles disagreement honestly and takes initiative at the right moments. The goal is to create a strong, tasteful default that can adapt to different people and situations. This work combines behavioral research, product thinking, research and communication taste. You will collaborate with product teams, human experts, and researchers across post-training and pretraining to ensure that improvements survive the full training stack and reach the models people use every day. In this role, you might - 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. You might thrive in this role if you - Think instinctively from the user’s perspective and care deeply about how models feel to work with, not only how they perform on benchmarks. - Can translate subjective-seeming product questions into falsifiable hypotheses and rigorous evaluations without losing the nuance that made the question important. - Care about preserving individuality, adaptability, and behavioral diversity rather than optimizing every model toward one narrow style. - Want to shape how frontier agents communicate, collaborate, and build trust with millions of people. - Have strong technical foundations in machine learning, software engineering, statistics, behavioral science, HCI, or a related field, and can quickly learn across unfamiliar parts of the stack. - Have strong taste for model behavior: you can look at user feedback and can explain why one response feels thoughtful, natural, and useful while another does not. - Have experience with LLMs, post-training, RL/RLHF, reward modeling, evals, synthetic data, pretraining data, or production ML systems. - Are excited by ambiguous capability problems where the signal is noisy, the failures are qualitative, and the solution may involve data, training, evals, product changes, or all of the above. - Can work effectively with researchers, engineers, product teams, designers, domain experts, human-data teams and safety boundaries, and can communicate clearly with each group. - Like building load-bearing systems and processes when that is what the team needs, even if the work is not glamorous. - Want to train and ship the models that make agents genuinely useful for developers, enterprises, researchers, and everyday users. About OpenAI Open

Strong technical foundations in machine learning, software engineering, statistics, behavioral science, HCI, or a related field; ability to quickly learn across unfamiliar parts of the stack. Experience with LLMs, post-training, RL/RLHF, reward modeling, evals, synthetic data, pretraining data, or production ML systems. Ability to translate subjective product questions into falsifiable hypotheses and rigorous evaluations. Capability to collaborate with researchers, engineers, product teams, designers, domain experts, human-data teams, and safety boundaries. Passion for building load-bearing systems and processes, and for shaping how frontier agents communicate, collaborate, and build trust.

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 rollout data and preference data. Improve reward models and RL objectives for model behaviors. Collaborate with pretraining and early-training teams on data mixtures, objectives, synthetic data, and upstream choices that shape downstream personality. Build sustainable pipelines for updating older training data as understanding evolves. Partner with product teams to turn consumer insight into model improvements and validate them in real workflows. Own projects end to end from observation to experimentation, training, evaluation, and launch.