Software Engineer, Codex Core Agents

The role

You will build infrastructure that powers Codex agents in production. This includes designing execution environments, orchestration systems, and state and memory systems for agents.

What you will do

• Design and build execution environments for AI agents, including sandboxing, isolation, and reproducibility.
• Develop systems for agent orchestration across multi-step, tool-using workflows.
• Build infrastructure for running, testing, and debugging code generated by models.
• Create state and memory systems that allow agents to persist context across long-running tasks.
• Optimize tokens, latency, reliability, and cost across Codex’s production fleet.
• Support model rollouts, capacity planning, and core tradeoffs between quality, speed, and economics.
• Build shared platform capabilities that unblock product teams, partner teams, and open source Codex.

Required qualifications

• Strong experience in distributed systems or infrastructure engineering.
• Built systems involving containers, sandboxing, or virtualization.
• Comfortable working across backend systems, APIs, and developer tooling.
• Care deeply about system reliability, performance, and security.
• Enjoy working on ambiguous, zero-to-one problems.
• Want to help build the systems that turn model capability into a dependable software engineering agent.

Nice to have

• Experience with code execution platforms, CI/CD systems, or build systems.
• Experience coding in Rust
• Familiarity with LLMs, agents, or tool-use frameworks.
• Background in security engineering or isolation systems.
• Experience building developer platforms, IDE tooling, or open source infrastructure.

Before you apply

• Background checks for applicants will be administered in accordance with applicable law.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.