Agent Post-Training, Computer Use Research

OpenAI
San Francisco
Workplace: OnsiteFull timeUSD 295,000 - 445,000 annuallyFunction: Education & TrainingSkills: ["Machine learning","Systems engineering","Research","Evaluation","Data pipelines"]

Join OpenAI’s Agent Post-Training, Computer Use team to teach models to operate computers—navigating desktops and browsers, using tools, and completing long-horizon tasks. You’ll design experiments, improve post-training pipelines, evaluate model behavior, and collaborate with Codex/ChatGPT product teams to ship reliable, production-ready agent capabilities.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
OpenAI
OpenAI
2 months ago

Agent Post-Training, Computer Use Research

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 15 hours agoStatus: Live

Job Summary

Join OpenAI’s Agent Post-Training, Computer Use team to teach models to operate computers—navigating desktops and browsers, using tools, and completing long-horizon tasks. You’ll design experiments, improve post-training pipelines, evaluate model behavior, and collaborate with Codex/ChatGPT product teams to ship reliable, production-ready agent capabilities.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Education & Training

Key Responsibilities

  • •Design and run experiments that improve agentic model behavior for complex computer use, including desktop and browser.
  • •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.

Pay and Benefits

Salary: USD 295,000 - 445,000 annually

Key Requirements

  • •Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field and ability to learn quickly across areas you haven't 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
  • •Ability to design hypotheses, build pipelines, run experiments, analyze results, and decide next steps
  • •Comfort working across research, product, infrastructure, data, evals, and safety boundaries and communicating clearly with multiple groups
  • •Desire to ship models that are useful for developers, enterprises, researchers, and everyday users
Experience:AIOpenAIMachine learningFrontier models
Skills:Machine learningSystems engineeringResearchEvaluationData pipelines
Languages:English
Tech Stack:RLRLHFRLAIFLLMsCodexChatGPTData pipelines

Company Brief

OpenAI
Develops and deploys advanced generative AI models (including ChatGPT and DALL·E) and AI infrastructure, providing APIs and consumer products to accelerate safe AGI for broad benefit.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Scaleup
Valuation: Hectocorn (USD 100B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2015
Glassdoor
Glassdoor: 4.4
WebsiteLinkedInGlassdoor