OpenAI
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
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
OpenAI
OpenAI builds AI infrastructure and products, including large-scale data center campuses for AI computing and generative AI applications for enterprise customers. The company is hiring civil engineers, project engineers, electrical design engineers, data center R&D engineers, and AI deployment engineers to expand its infrastructure capabilities and help customers deploy AI solutions.
View all jobs at OpenAILikely interview questions
- Describe your experience building distributed systems at scale. What were the key challenges around reliability, latency, or cost optimization?
- Tell us about a time you designed or implemented sandboxing, containerization, or code execution infrastructure. What isolation and security concerns did you have to address?