Senior AI Agents Infrastructure Engineer

OpenAI, Inc.; City Of London; On-site; GBP 130,000 - 190,000; Full time

Job summary

OpenAI seeks engineers to build the infra powering Codex agents in production. This role focuses on systems that let models safely execute code, interact with tools, complete long-running tasks, and operate reliably and efficiently at scale.

You'll design and operate the infrastructure behind sandboxed execution, orchestration, stateful workflows, app-server and SDK boundaries, and model rollouts. You'll work at the intersection of distributed systems, developer tooling, and AI, building

Qualifications

• Experience in distributed systems and infra engineering.
• Built systems with containers, sandboxing or virtualization.
• Comfort working across backend systems, APIs and developer tooling.
• Care about reliability, performance and security in production.
• Able to tackle ambiguous, zero-to-one problems.
• Desire to build developer platforms and open infrastructure.

Responsibilities

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

Skills

Distributed systems

Infrastructure engineering

Containers

Sandboxing

Backend systems

APIs

Developer tooling

Reliability

Performance

Security

Tools

Rust

CI/CD systems

Build systems

Job description

OpenAI seeks engineers to build the infra powering Codex agents in production. This role focuses on systems that let models safely execute code, interact with tools, complete long-running tasks, and operate reliably and efficiently at scale.

You'll design and operate the infrastructure behind sandboxed execution, orchestration, stateful workflows, app-server and SDK boundaries, and model rollouts. You'll work at the intersection of distributed systems, developer tooling, and AI, building