Applied AI Engineer, Codex Core Agent

OpenAI's Codex Core Agent team is hiring an Applied AI Engineer to improve Codex agents from demos to dependable tools. You will design and iterate on agent behaviors, build evals, and improve performance via prompting, tool-use, and context construction. This role works closely with research, infrastructure, and product teams to ship measurable gains in solve rate and real-world usefulness.

• Design and iterate on agent behaviors across real-world coding tasks and long-horizon workflows.
• Develop and run evals to measure agent performance, regressions, failure modes, and edge cases.
• Improve performance through prompting, tool-use strategies, context construction, and model-facing experimentation.
• Analyze production failures and systematically improve robustness and reliability.
• Build feedback loops and data systems that get better real-task data into evaluation and research.
• Partner with product teams to shape user-facing agent experiences and interfaces.

• Experience building or shipping machine learning or LLM-powered products.
• Strong Python skills and comfort with modern ML tooling.
• Experience with model evaluation, fine-tuning, or prompt design.
• Systems-oriented thinking focused on user outcomes, not just model metrics.
• Comfort debugging messy, real-world failures and turning them into improvements.