other
Posted Jun 26Agent Post-Training, API & Power Users
at openai
San Francisco, United StatesOn-site
Responsibilities
- - Build evals, graders, and environments from real developer and power-user workflows, then turn observed failures into training data, model-behavior hypotheses, and shipped improvements.
- - Own end-to-end model behavior projects, from qualitative failure analysis through data generation, training experiments, eval design, integration into major runs, and launch readiness.
Requirements
- 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 build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use.
- ABOUT THE ROLE As a member of this API & power-users team, you will improve the capabilities, reliability, and product fit of OpenAI’s agentic models for power users and API developers.
- YOU MIGHT THRIVE IN THIS ROLE IF YOU - Have strong technical fundamentals in ML, software engineering, systems, statistics, or applied research, and can quickly learn across unfamiliar parts of the stack. - Have hands-on
- experience with LLMs, post-training, RL/RLHF/RLAIF, evals, graders, synthetic data, coding agents, tool-using agents, API products, or production ML systems.
- About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence
Additional details
- 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 is where new model capabilities get made.
- You might design evals from real developer workflows, build training environments around production-like tool use, turn qualitative model failures into training data, evals, or post-training interventions, or drive a behavior improvement from discovery through post-training, integration, and launch.
- The strongest candidates are comfortable turning ambiguous model behavior problems into concrete progress, whether that means improving tool use, planning, instruction following, recovery from mistakes, or how models behave in API-based workflows.
- You should be excited to work across research, engineering, data, evals, and product to make models better at acting in real workflows.
- You will work closely with researchers, engineers, API/product teams, Codex, infrastructure, and safety/alignment partners to decide which behaviors matter, how to measure them, how to train them, and when they are ready for major model runs.
- This is a high-agency role for people who want their work to show up directly in frontier models used by expert users and developers.
- IN THIS ROLE, YOU MIGHT - Design and run experiments that improve model behavior in API and power-user workflows: function calling, tool use, coding, planning, long-horizon execution, factuality, instruction following, error recovery, and calibrated reasoning.
- - Partner with API and power-users to identify high-leverage behavior gaps and convert product signals into post-training interventions.