Applied AI Engineer: Codex Core Agent - Real-World Impact

Fdetimes; San Francisco (CA); Hybrid; USD 150,000 - 210,000; Full time

Job summary

OpenAI is seeking applied AI engineers to advance Codex agent capabilities from demos to dependable tools. You will join a cross-functional team to improve agent performance on real software tasks and measure gains in solve rate, usefulness, and value for users.

You’ll work with research, infrastructure, and product to ship practical improvements, focusing on robustness, steerability, and real-world applicability across end-to-end tasks.

Qualifications

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

Responsibilities

• Design and iterate on agent behaviors for real-world coding tasks and long-horizon workflows.
• Collaborate with research to run evals measuring 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 real-world task data into evaluation and research.
• Partner with product teams to shape user-facing agent experiences and interfaces.

Skills

Python

ML tooling

Model evaluation

Fine-tuning

Prompt design

Debugging

Agent frameworks

Tools

PyTorch

TensorFlow

Job description

OpenAI is seeking applied AI engineers to advance Codex agent capabilities from demos to dependable tools. You will join a cross-functional team to improve agent performance on real software tasks and measure gains in solve rate, usefulness, and value for users.

You’ll work with research, infrastructure, and product to ship practical improvements, focusing on robustness, steerability, and real-world applicability across end-to-end tasks.