Software Engineer, Agent Platform

About the Team The Agent Platform team at OpenAI builds the production systems that bring useful AI agents to users around the world. We provide the platform that enables agents to execute code, use tools, and interact with software reliably and securely at scale. We work closely with product, research, and infrastructure teams to turn new agent capabilities into dependable product experiences. Our work spans the execution environments, APIs, and integrations that support agentic products such as Codex and tool use in ChatGPT. We focus on how agents run in production: making it easy to launch new capabilities, supporting growing demand, and improving the performance and reliability of the systems behind user experiences. Some of the hardest problems in making agents useful emerge when they meet real-world workloads. We build the platform that helps agents handle those workloads safely, recover when things go wrong, and deliver consistent results. About the Role As a Software Engineer on the Agent Platform team, you will build and scale the services that power agentic products at OpenAI. You’ll work closely with product engineers, researchers, and infrastructure engineers to bring new capabilities from early prototypes to production. Your work will include designing APIs and services, improving agent execution and orchestration, and building the integrations needed to support increasingly capable agents. You’ll help launch new experiences while strengthening the reliability, observability, and efficiency of the platform underneath them. We’re looking for engineers with experience building large-scale backend systems or infrastructure who enjoy working close to products and users. You should be comfortable moving quickly through ambiguous problems while making thoughtful decisions about security, performance, and long-term maintainability. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. In this role, you will: - Build and operate production services that enable agents to execute code, use tools, and interact with external systems. - Design APIs and platform abstractions that make it easier for product teams to build and launch agentic experiences. - Develop orchestration systems that manage agent execution, state, resource allocation, retries, and recovery. - Improve platform reliability, latency, and efficiency through performance optimization, observability, and capacity planning. - Partner with product, research, security, and infrastructure teams to bring new agent capabilities into production. - Own systems through their full lifecycle, from design and implementation to rollout, monitoring, and ongoing operation. You might thrive in this role if you: - Have experience building and operating large-scale backend services, distributed systems, or cloud infrastructure. - Enjoy building shared platforms and APIs that help other engineers move faster. - Can take an early prototype, turn it into a reliable service, and evolve it as usage grows. - Have a strong understanding of system performance, concurrency, failure modes, and resource management. - Care about how infrastructure decisions affect the user experience, including responsiveness, reliability, and predictable behavior. - Are comfortable working across service boundaries and collaborating with teams to solve problems from end to end. - Have experience with cloud platforms, containers, orchestration systems, or infrastructure-as-code tools such as Terraform. - Are interested in secure execution environments, sandboxing, and the challenges of running agent workloads in production. About OpenAI OpenAI is an AI research and deploy