Applied AI Engineer, Codex Core Agent

The role

Applied AI engineers will improve agent performance on real software engineering tasks. You will work across research, infrastructure, and product to turn model potential into dependable tools.

What you will do

• Design and iterate on agent behaviors across real-world coding tasks and long-horizon workflows.
• Work closely with research to 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 failures in production and systematically improve robustness and reliability.
• Build feedback loops and data systems that get better real-task data into evaluation and research.
• Work with product teams to shape user-facing agent experiences and the interfaces the agent depends on.
• Help define what good looks like for agents completing complex tasks end-to-end.

Required qualifications

• Experience building or shipping machine learning or LLM-powered products.
• Strong in Python.
• Comfortable with modern ML tooling.
• Worked on model evaluation, fine-tuning, or prompt design.
• Think in terms of systems and user outcomes, not just model metrics.
• Enjoy debugging messy, real-world failures and turning them into improvements.

Nice to have

• Experience with agent frameworks or tool-using LLM systems.
• Research experience with code generation models or developer tooling.
• Experience working with large, messy datasets or production logs.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.