Agent Post-Training, Connectors Research

Details

The Agent Post-Training team creates frontier agents for Codex, ChatGPT, the API, and other products. The team develops training data, environments, graders, training methods, and feedback loops for capabilities including coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and agent behavior.

The role focuses on teaching models to interface with professional software through code, APIs, tools, and structured integrations. Relevant applications include Slack, Google Workspace, GitHub, Notion, Linear, Salesforce, and other enterprise systems. The work enables agents to find information, update systems, coordinate work, generate artifacts, and complete multi-step workflows.

Responsibilities

• Design and run experiments to improve agentic model behavior for complex software and plugins.
• 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, then turn those failures into training data, product fixes, or research directions.
• Partner with Codex and ChatGPT product teams to translate user and product signals into model improvements.
• Work on early-training and alignment interventions, including data mixtures, objectives, synthetic data, and evaluation loops.
• Help determine which integrations, capabilities, and fixes are ready for major model runs.
• Improve large-scale training and launch machinery, including experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
• Work on cross-functional projects involving model training, product infrastructure, and the production agent harness, including multi-agent systems and production-like environments.
• Debug failures in shipped or near-shipped models and turn qualitative behavior into hypotheses, experiments, and fixes.

Requirements

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field.
• Hands-on experience with large language models, reinforcement learning, RLHF/RLAIF, post-training, evaluations, graders, synthetic data, model training, coding agents, tool-using agents, or production machine learning systems.
• Ability to work on open-ended problems with noisy signals using both research judgment and engineering execution.
• Interest in product impact and model behavior, including making agents useful, reliable, honest, tasteful, and easy to work with.
• Ability to turn behavioral problems into concrete experiments by defining hypotheses, building pipelines, running models, analyzing results, and determining next steps.
• Ability to work across research, product, infrastructure, data, evaluations, and safety teams and communicate clearly with each group.
• Willingness to build reliable systems and processes as needed.

Benefits

• Medical, dental, and vision insurance with employer contributions to Health Savings Accounts.
• Pre-tax accounts for health, dependent care, and commuter expenses.
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off, company holidays, office closures, and applicable paid sick or safe time.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Equity and performance-related bonuses for eligible employees.

OpenAI is an equal opportunity employer committed to reasonable accommodations and compliance with applicable employment laws.