Agent Post-Training & Connectors Research Lead

OpenAI; California (MO); On-site; USD 180,000 - 260,000; Full time

Job summary

OpenAI is seeking a high‑agency specialist in Agent Post‑Training, Connectors to teach models how to interface with top professional software through code, APIs, tools, and structured integrations across Slack, Google Workspace, GitHub, Notion, Linear, Salesforce and more. You will collaborate with researchers, engineers, product and safety teams to decide what to ship and measure results.

You will drive end‑to‑end improvements to the post‑training stack, design experiments, and build evaluation

Qualifications

• Strong fundamentals in ML, software engineering, systems, or statistics.
• Hands-on experience with LLMs, RL/LHF/RLAIF, post-training, evals, and synthetic data.
• Experience coding agents, tool-using agents, and production ML systems.
• Ability to move from research ideas to concrete experiments and results.

Responsibilities

• Design and run experiments that improve agentic model behavior for complex software and plugins.
• 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 next model failures, then turn them into training data, fixes, or new research directions.
• Partner with Codex and ChatGPT product teams to translate user needs into model improvements.
• Work on early-training and alignment interventions, including data mixtures and eval loops.
• Help decide which integrations and fixes are ready for major model runs.
• Improve machinery for large-scale training and launch: velocity, reliability, observability, reproducibility, cost, latency, production readiness.
• Take on cross-functional projects touching model training, product infrastructure, and production harness.

Skills

Machine learning

Software engineering

Systems

Statistics

LLMs

RLHF/RLAIF

Post-training

Eval pipelines

Synthetic data

Model training

Tool integration

Production ML

Tools

Slack

Google Workspace

GitHub

Notion

Linear

Salesforce

Job description

OpenAI is seeking a high‑agency specialist in Agent Post‑Training, Connectors to teach models how to interface with top professional software through code, APIs, tools, and structured integrations across Slack, Google Workspace, GitHub, Notion, Linear, Salesforce and more. You will collaborate with researchers, engineers, product and safety teams to decide what to ship and measure results.

You will drive end‑to‑end improvements to the post‑training stack, design experiments, and build evaluation