Agent Post-Training, Computer Use (AI)

Location: San Francisco, United States

Base salary: $380,000–$500,000 annually, plus equity, performance-related bonuses, and benefits.

Company

OpenAI is an AI research and deployment company developing general-purpose artificial intelligence and deploying it through products including Codex, ChatGPT, and the API.

What you will do

• Design and run experiments that improve agentic model behavior for complex computer-use tasks across desktops and browsers.
• Own end-to-end improvements to the post-training stack, including reinforcement learning, data pipelines, graders, reward signals, evaluations, diagnostics, and model-behavior analysis.
• Build evaluations and environments that expose model failures and convert them into training data, product fixes, or research directions.
• Partner with research, engineering, product, infrastructure, data, and safety/alignment teams to translate product signals into model improvements and determine readiness for major model runs.
• Improve large-scale training and launch systems for experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
• Debug difficult failures in shipped or near-shipped models and develop concrete hypotheses, experiments, and fixes.

Requirements

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field, with the ability to learn quickly across unfamiliar areas.
• Hands-on experience with LLMs, reinforcement learning, RLHF/RLAIF, post-training, evaluations, graders, synthetic data, model training, coding agents, tool-using agents, or production ML systems.
• Ability to turn an open-ended behavioral problem into a hypothesis, pipeline, model run, analysis, and next-step decision.
• Ability to work across research, product, infrastructure, data, evaluation, and safety boundaries and communicate clearly with each group.
• Interest in product impact and model behavior, including making agents useful, reliable, honest, tasteful, and easy to work with.
• Willingness to build load-bearing systems and processes when required by the team.

Culture & Benefits

• Work directly on frontier agent capabilities used by developers, enterprises, researchers, and everyday users.
• Medical, dental, and vision insurance with employer HSA contributions, plus health and dependent-care FSAs.
• 401(k) retirement plan with employer match, paid parental, medical, caregiver, sick, and safe leave, flexible PTO for exempt employees, and paid holidays.
• Mental health and wellness support, employer-paid life and disability coverage, and an annual learning and development stipend.
• Daily office meals, eligible meal delivery credits, relocation support for eligible employees, and other wellness and charitable benefits.

Hiring process

• Benefits and additional employment details are provided during the hiring process.
• Background checks are administered in accordance with applicable law.