Agent Post-Training API and Power Users

11 hours agoSalary: 380K - 500KSan Francisco, USAResearchJobs by OpenAI

AI research and deployment company building and deploying frontier AI products, including ChatGPT, Codex, and its API platform.

Recently funded151 current maintainers88 active leads20 new active leads99 lead step-downs12 early lead departuresTeam intelligence

Maintainer signals as of 9/25/2026

San Francisco, United States
About OpenAI

OpenAI’s mission is to ensure artificial general intelligence benefits all of humanity. It consists of the nonprofit OpenAI Foundation and OpenAI Group, a public benefit corporation governed by the Foundation.

View jobs by OpenAI

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will improve the capabilities, reliability, and product fit of agentic models for API developers and power users. You will design experiments, build evaluations and training environments, turn model failures into training interventions, and lead model-behavior projects through integration and launch.

Requirements

  • Technical fundamentals in machine learning, software engineering, systems, statistics, or applied research
  • Experience with LLMs, post-training, RL, RLHF, RLAIF, evaluations, graders, synthetic data, coding agents, tool-using agents, API products, or production ML systems
  • Ability to analyze model behavior and form training hypotheses
  • Experience working across research, product, infrastructure, data, evaluation, and safety functions

Responsibilities

  • Design and run experiments to improve agentic model behavior
  • Build evaluations, graders, and training environments from developer workflows
  • Turn observed model failures into training data and post-training interventions
  • Identify behavior gaps with API and power users
  • Improve tool use, planning, instruction following, error recovery, and multi-step coherence
  • Lead model-behavior projects from failure analysis through launch readiness
  • Develop feedback loops from power-user traces and API usage patterns
  • Debug failures in shipped or near-shipped models
  • Improve training and launch reliability, observability, reproducibility, cost, and latency

Benefits

  • Medical, dental, and vision insurance with employer Health Savings Account contributions
  • Pre-tax health, dependent-care, parking, and transit accounts
  • 401(k) retirement plan with employer match
  • Paid parental, medical, and caregiver leave
  • Flexible PTO or up to 15 days of annual PTO depending on employee classification
  • Paid holidays, company office closures, and sick or safe time
  • Mental health and wellness support
  • Employer-paid basic life and disability coverage
  • Daily office meals and eligible meal-delivery credits
  • Relocation support for eligible employees
  • Charitable donation matching and wellness stipends may be provided