Researcher, Artifacts - Agent Post-Training

OpenAI•San Francisco, CA

8d•$250,000 - $380,000

About The Position

The Agent Post-Training team at OpenAI is responsible for training frontier agents that are shipped to the world, including models for Codex, ChatGPT, and the API. These agents are designed to be persistent, proactive intelligences capable of operating computers, collaborating with people and other agents, and expanding human potential. The team defines future agent capabilities, develops the training signals for these abilities, and conducts experiments to realize them. Their work encompasses areas such as coding, tool use, computer operation, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. This team is central to the creation of new model capabilities, building the data, environments, graders, training methods, and feedback loops that shape OpenAI's next generation of agents and bring them into production. As a member of the Agent Post-Training, Artifacts team, you will focus on training frontier models to produce polished and useful work products, including documents, spreadsheets, slide decks, dashboards, reports, analyses, and other interactive or editable artifacts. The role involves teaching models to transform vague user goals into finished artifacts with strong structure, visual appeal, domain judgment, correctness, and low latency. This requires owning improvements across the post-training stack, including Reinforcement Learning (RL), data pipelines, graders, reward signals, evaluations (evals), and behavioral analysis. You will collaborate with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to determine content for major model runs, measure their success, and implement improvements in products used by real people. This is a high-agency role for individuals who want their work to directly impact frontier models.

Requirements

Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field, and can learn quickly across the parts you have not worked in before.
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.
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. You have 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.
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.

Nice To Haves

Some prior background in consulting, finance, marketing, operations, or data science.

Responsibilities

Design and run experiments that improve agentic model behavior for complex software and plugins.
Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, reward signals, evals, diagnostics, and model-behavior analysis.
Build evals and environments that expose the next set of model failures, then turn those failures into training data, product fixes, or new research directions.
Partner with Codex and ChatGPT product teams to understand what users need and translate product signal into model improvements.
Work on early-training and alignment interventions, including data mixtures, objectives, synthetic data, and eval loops that shape downstream agent behavior.
Help decide which integrations, capabilities, and fixes are ready for inclusion in major model runs.
Improve the machinery for large-scale training and launch: experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
Take on cross-functional projects that touch model training, product infrastructure, and the production agent harness, such as multi-agent systems or training directly against production-like environments.
Debug hard failures in shipped or near-shipped models and turn messy qualitative behavior into concrete hypotheses, experiments, and fixes.