Software Engineer, Codex Core Agents

About this role

Build production infrastructure for AI agents at OpenAI, focusing on sandboxed execution, orchestration, and reliable scaling. Design systems that enable models to safely run code, use tools, and operate efficiently across long-running tasks in a distributed environment.

What you'll do

• Design and build execution environments with sandboxing, isolation, and reproducibility for AI agents
• Develop orchestration systems for multi-step, tool-using agent workflows
• Create infrastructure for running, testing, and debugging model-generated code
• Build state and memory systems for agents to persist context across long-running tasks
• Optimize token usage, latency, reliability, and cost across production fleet
• Support model rollouts, capacity planning, and quality-speed-cost tradeoffs at scale

What they're looking for

• Distributed systems and infrastructure engineering
• Container, sandboxing, or virtualization technologies
• Backend systems, APIs, and developer tooling
• System reliability, performance, and security design
• Code execution platforms or CI/CD systems
• LLMs, agents, or tool-use frameworks
• Security engineering and isolation systems
• Developer platform or IDE tooling