Agent Post-Training Research

Highlights

• Train frontier agents shipped in Codex, ChatGPT, and the API.
• Own agentic capabilities from idea through training run to launch.
• Build evals and training signals that shape next-gen agent behavior.

Ideal candidate

High-agency builder with strong ML and engineering fundamentals who thrives on ambiguous problems and cares about shipping reliable, useful agents that work in the real world.

Requirements

• Have strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field, and can learn quickly across parts you have not worked in before.
• Have hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, model training, coding agents, tool-using agents, or production ML systems.
• Are excited by open-ended problems where the path is unclear, the signal is noisy, and the right answer requires both research taste and engineering execution.
• Care about product impact and model behavior, not just benchmark movement, with opinions about what makes an agent useful, reliable, honest, tasteful, and easy to work with.
• Can move from a vague behavioral problem to a concrete experiment: define the hypothesis, build the pipeline, run the model, analyze the result, and decide what to do next.
• Are comfortable working across research, product, infrastructure, data, evals, 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.