AI Agent Infrastructure Engineer

OpenAI

California (MO)

On-site

USD 180,000 - 240,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

OpenAI is seeking engineers to build the infrastructure powering Codex agents in production. You will design execution environments, orchestration for multi-step tool-using workflows, and scalable runtimes for model-generated code.

You will optimize performance, latency, and cost while maintaining safety and reliability across the production fleet. Join a team that bridges distributed systems, developer tooling, and AI to turn model capabilities into dependable software infrastructure for

Qualifications

Experience in distributed systems or infrastructure engineering.
Experience with containers, sandboxing, or virtualization.
Experience with backend systems, APIs, and developer tooling.
Strong focus on reliability, performance, and security.
Interest in zero-to-one, ambiguous problems.
Ability to build developer platforms, IDE tooling, or open source infrastructure.

Responsibilities

Design and operate the infrastructure behind sandboxed execution for Codex agents, including 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 for frontier agents at scale.
Build shared platform capabilities that unblock product teams, partner teams, and open source Codex.