Applied AI Engineer: Build Real-World Codex Agents

openai; General Trias; Remote; PHP 5,621,000 - 9,369,000; Full time

Job summary

OpenAI is seeking applied AI engineers to advance Codex agents from demos to dependable tools. You will improve agent performance on real software tasks, coordinating with research, infra, and product to ensure usefulness, steerability, and reliability in practice.

You’ll focus on turning research capabilities into measurable gains in solve rate, usefulness, and economic value for users, while pushing for robust, real-world applicability.

Qualifications

• Experience building or shipping ML/LLM-powered products.
• Strong Python proficiency and modern ML tooling.
• Experience with evaluation, fine-tuning, or prompt design.

Responsibilities

• Design and iterate agent behaviors for 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 to feed evaluation and research with real-task data.
• Collaborate with product teams to shape user-facing agent experiences.

Skills

Python

ML tooling

Model evaluation

Fine-tuning

Prompt design

System thinking

Tools

Job description

OpenAI is seeking applied AI engineers to advance Codex agents from demos to dependable tools. You will improve agent performance on real software tasks, coordinating with research, infra, and product to ensure usefulness, steerability, and reliability in practice.

You’ll focus on turning research capabilities into measurable gains in solve rate, usefulness, and economic value for users, while pushing for robust, real-world applicability.