Applied AI Engineer — Codex Core Agent

OpenAI; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

OpenAI is seeking applied AI engineers to advance Codex agents from demos to dependable tools in London. You will focus on improving agent performance on real software tasks, making improvements practical, measurable, and valuable for users.

The role involves collaborating with research, infra, and product to ensure agents are powerful, steerable, and reliable in practice. Join a team shaping the future of agent technology, with emphasis on robustness, evaluation, and real-world impact across

Qualifications

• Experience shipping ML/LLM-powered products.
• Strong Python and ML tooling skills.
• Experience with evaluation, fine-tuning, or prompt design.
• Think in terms of systems and user outcomes.

Responsibilities

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

Skills

Python

ML tooling

Model evaluation

Prompt design

Systems thinking

Debugging

Job description

OpenAI is seeking applied AI engineers to advance Codex agents from demos to dependable tools in London. You will focus on improving agent performance on real software tasks, making improvements practical, measurable, and valuable for users.

The role involves collaborating with research, infra, and product to ensure agents are powerful, steerable, and reliable in practice. Join a team shaping the future of agent technology, with emphasis on robustness, evaluation, and real-world impact across