Software Development · San Francisco, CA

Hybrid Full-time

Software Engineer, Product Infrastructure - Agent Runtime

OpenAI · San Francisco, CA · Posted Aug 17, 2026

This posting comes from OpenAI. Confirm the details on their site before applying.

Overview

Agent Runtime builds the shared agent primitives and compute runtime that power OpenAI products and applications. As agents take on more complex, longer-running tasks, we build the systems that let them maintain state, use tools, and work reliably in the environments they need. We work closely with Research, Product, and infrastructure teams to turn advances in model capabilities into useful products.

Responsibilities

  • Design, build, and operate backend services, APIs, and reusable runtime primitives that support agent experiences across products.
  • Build systems for persistent agent state, asynchronous execution, orchestration, and progress reporting so agents can carry work forward over time.
  • Develop infrastructure that connects agents with tools and execution environments, with clear interfaces and safe, reliable behavior.
  • Improve reliability, scalability, and performance through observability, production debugging, failure recovery, and thoughtful system design.
  • Partner with Product, Research, and engineering teams to turn emerging capabilities and customer needs into reusable infrastructure.
  • Own projects end to end, balancing rapid iteration with maintainable architecture and the operational demands of systems used across products.

Requirements

  • 7+ years of professional software engineering experience, with substantial ownership of backend systems, product infrastructure, or developer platforms.
  • A track record of designing, shipping, and operating production services, APIs, and data models that support complex product workflows.
  • Strong distributed systems fundamentals and experience reasoning about state, concurrency, asynchronous work, and failure recovery.
  • Experience building production systems in Python, Go, Rust, TypeScript, or similar languages, and the ability to work across service and infrastructure boundaries.
  • Experience improving reliability and performance, using observability and debugging to understand system behavior and resolve production issues.
  • Strong product judgment and developer empathy, with an ability to translate ambiguous needs into clear APIs, useful abstractions, and pragmatic technical tradeoffs.
  • An ability to collaborate across product and infrastructure teams, communicate design decisions clearly, and take ownership from early exploration through production.
  • Interest in AI agents and how they execute real work. Experience with agent runtimes, workflow orchestration, or execution environments is helpful but not required.

Great fits start here.

Whether you're looking for your next role or your next team member, give people and possibilities a place to meet.