Researcher, Connectors - Agent Post-Training

📋 Description

• Design and run experiments to improve agentic model behavior.
• Own end-to-end improvements to the post-training stack (RL, data pipelines, evals).
• Build evals and environments to surface failures and turn them into data or fixes.
• Partner with Codex/ChatGPT teams to translate product signals into model improvements.
• Work on early-training and alignment interventions (data mixtures, synthetic data).
• Help decide which integrations and fixes are ready for major model runs.

🎯 Requirements

• Strong fundamentals in ML, software engineering, systems, or statistics.
• Hands-on with LLMs, RL/RLHF/RLAIF, post-training, evals, synthetic data.
• Able to learn quickly across unfamiliar areas.
• Open-ended problems requiring research taste and engineering.
• Focus on product impact and model behavior, not just benchmarks.
• Define hypotheses, build pipelines, run experiments, analyze results.
• Cross-functional collaboration across research, product, infra, data, safety.
• Enjoy building scalable, robust systems and processes.

🎁 Benefits

• Equal opportunity employer.
• Reasonable accommodations available for applicants with disabilities.
• OpenAI Global Applicant Privacy Policy.