The opportunity
API Agents builds the shared agent harness, tools, and infrastructure that turn OpenAI’s frontier models into systems that can reliably complete real work. We carry the capabilities behind Codex into a much broader set of products and workflows across software engineering,…
What you'll do
Design, build, and operate the shared agent harness and backend: infrastructure that power long-running, high-value workflows across OpenAI and third-party products.
Build reusable capabilities across search and connected context, computer: use, memory, tool execution, delegation, subagents, and multi-agent orchestration.
Establish the foundations agents need to operate safely in production,: including secure execution environments, identity and permissions, observability, evaluations, reliability, and cost and latency efficiency.
Partner with Research, Codex, infrastructure, applied product teams, and: external developers to translate model progress, traces, evaluations, and real workflow needs into shared capabilities and measurable gains in task completion, cost, and latency.
+ years of professional engineering experience, excluding internships, in: relevant backend, infrastructure, platform, or product-driven engineering roles.
Exceptional backend engineering fundamentals and a track record of leading: complex systems from ambiguous problem statements to reliable production services.
What they're looking for
- Proficiency in one or more backend languages such as Python, Go, Rust,: TypeScript, or similar, with the ability to move comfortably across service, platform, and product boundaries.
- Strong systems design and operational judgment across distributed systems,: APIs, workflow orchestration, search or storage, compute and execution, identity and permissions, or observability and reliability.
- Infrastructure depth paired with product judgment: you can abstract complex systems into simple, durable primitives that other engineers and developers can build on.
- Strong developer empathy and communication skills, including experience: partnering with users, research teams, and product engineers to make fast-moving capabilities useful and dependable.
