Agent Post-Training Personality Engineer

OpenAI; California (MO); On-site; USD 180,000 - 280,000; Full time

Job summary

OpenAI is seeking a role on the Agent Post-Training team to help shape the behavior and collaboration capabilities of our frontier agents. You will translate qualitative insights into evals, training data, reward signals, and model improvements, ensuring agents are thoughtful, proactive, and easy to work with across diverse contexts.

You will collaborate across post-training and pretraining, with product teams, researchers, and human-experts to build robust evaluation pipelines, data flows, and

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, 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.

Skills

ML foundations

Software engineering

Statistics

Behavioral science

HCI

LLMs experience

RL/RLHF

Reward modeling

Data synthesis

Production ML systems

Job description

OpenAI is seeking a role on the Agent Post-Training team to help shape the behavior and collaboration capabilities of our frontier agents. You will translate qualitative insights into evals, training data, reward signals, and model improvements, ensuring agents are thoughtful, proactive, and easy to work with across diverse contexts.

You will collaborate across post-training and pretraining, with product teams, researchers, and human-experts to build robust evaluation pipelines, data flows, and