About the job
We’re looking for engineers to build the infrastructure that powers Codex agents in production. This role focuses on the systems that let models safely execute code, interact with tools, complete long-running tasks, and operate reliably and efficiently at scale.
Responsibilities
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 the core tradeoffs between quality, speed, and economics to manage a fleet of frontier agents at scale.
Build shared platform capabilities that unblock product teams, partner teams, and open source Codex.
Qualifications
Minimum
Have strong experience in distributed systems or infrastructure engineering.
Have built systems involving containers, sandboxing, or virtualization.
Are 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.
Preferred
Experience with code execution platforms, CI/CD systems, or build systems.
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.