Applied AI Engineer, Codex Core Agent: Build Reliable Tools

OpenAI; California (MO); On-site; USD 180,000 - 250,000; Full time

Job summary

OpenAI is seeking an Applied AI Engineer to advance Codex agents from demos to dependable tools. You will focus on improving agent performance on real software tasks and turn research into measurable practical value.

You will collaborate with research, infrastructure, and product to ensure agents are powerful, steerable, and reliable in practice. The role emphasizes robustness, evaluation, and user-facing interfaces that deliver meaningful outcomes.

Qualifications

• Experience shipping ML or LLM-powered products.
• Strong Python and ML tooling background.
• Experience with model evaluation, fine-tuning or prompt design.

Responsibilities

• Design and iterate on agent behaviors across real-world coding tasks and long-horizon workflows.
• Develop evals with research to measure performance, regressions, and edge cases.
• Improve performance via prompting, tool-use strategies, and context construction.
• Analyze production failures and improve robustness and reliability.
• Build data systems that turn real-task data into evaluation signals.
• Collaborate with product teams to shape user-facing agent experiences.

Skills

Python

ML tooling

Model evaluation

Prompt design

Systems thinking

Debugging real-world failures

Tools

Agent frameworks

LLM tooling

Large datasets

Job description

OpenAI is seeking an Applied AI Engineer to advance Codex agents from demos to dependable tools. You will focus on improving agent performance on real software tasks and turn research into measurable practical value.

You will collaborate with research, infrastructure, and product to ensure agents are powerful, steerable, and reliable in practice. The role emphasizes robustness, evaluation, and user-facing interfaces that deliver meaningful outcomes.