About the TeamThe Cloud Agents team builds product infrastructure for long-running agents in the cloud: orchestration, sandboxing and isolation, secure environment connectivity, secrets and identity, observability, reliability, and cost controls. These agents securely connect to diverse developer and customer environments and use tools to accomplish goals. We partner closely with product, research, and infrastructure teams to turn agentic capabilities into dependable platforms for OpenAI products and developers building on OpenAI.
About the RoleWe are looking for an experienced software engineer to help build and scale our cloud agent platform. You will design and operate systems for orchestrating agents at scale. You will work closely with product engineers on ChatGPT, API, and Codex to define the right abstractions and enable them to ship products quickly. Strong backend or infrastructure experience is important; experience with Python, Rust, distributed systems, cloud infrastructure, or product platforms is especially helpful.
In this role, you will:- Design and scale the orchestration, sandboxing and storage systems that run agentic workloads for Codex, ChatGPT, and the OpenAI API.
- Partner with product engineers to build a platform that enables them to ship quickly and turn feedback into robust abstractions.
- Improve reliability, security, performance, and cost efficiency for long-running agents.
- Deploy services that can operate across different environments and clouds.
Your background might look something like:- 9+ years of professional engineering experience, excluding internships, in relevant roles at technology and product-driven companies.
- Experience leading large-scale backend, platform, or infrastructure projects from ambiguous problem statements to production systems.
- Proficiency in one or more backend languages such as Python, Go, Rust, TypeScript, or similar, and the ability to move across service, platform, and product boundaries.
- Strong understanding of distributed systems, cloud platforms, and production reliability.
- Enjoy abstracting away complex infrastructure and building platforms for product engineers to move faster.
- Care about building platforms for other engineers and developers, and enjoy working closely with users to make complex infrastructure feel simple.
- Comfort with a fast-moving pace while caring for security and operational excellence.
