Software Development · San Francisco, CA

Hybrid Full-time

Software Engineer, Agent Identity

OpenAI · San Francisco, CA · Posted Nov 18, 2026

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

Overview

The Agent Identity team builds the foundational identity infrastructure that enables AI agents to securely act on behalf of users and organizations. We develop the systems that allow agents to establish their identity, demonstrate whose authority they are operating under, and securely access resources across applications and environments. Our team owns agent identity and delegation, authentication and authorization, credential lifecycle management, revocation, and integrations with external platforms.

Responsibilities

  • Design and build foundational agent identity primitives, including agent authentication, delegated authorization, and credential lifecycle management.
  • Develop secure mechanisms that enable agents to act on behalf of users and organizations across internal and external systems.
  • Architect authentication and authorization flows for connectors, third-party applications, and cloud-based agent execution environments.
  • Build and evolve Sign in with ChatGPT, enabling secure identity federation and interoperability across the broader application ecosystem.
  • Design highly scalable, reliable, and secure distributed systems that support credential issuance, rotation, revocation, and access enforcement.
  • Partner closely with engineering, product, security, and external platform teams to solve emerging identity challenges and help shape industry standards.
  • Drive technical direction and own complex initiatives from initial architecture through production deployment.

Requirements

  • Have experience designing, building, and operating large-scale distributed systems or business-critical backend infrastructure.
  • Have deep technical experience in identity and access management, workload identity, identity providers, authentication, authorization, or credential lifecycle management.
  • Alternatively, have experience building cloud-based AI agents, agent execution environments, browser-based automation, or connector infrastructure, with firsthand exposure to identity and authentication challenges.
  • Have familiarity with identity and authorization protocols such as OAuth 2.0, OpenID Connect, or related emerging standards.
  • Bring a security-first mindset and proactively consider trust boundaries, failure modes, and potential abuse when designing systems.
  • Thrive in ambiguous problem spaces where established technical patterns may not yet exist, and enjoy defining solutions from first principles.
  • Have a track record of driving complex technical initiatives, influencing architectural decisions, and collaborating effectively across engineering teams.
  • Are excited about defining how identity, trust, and delegated authority will work in a world where AI agents increasingly act on our behalf.

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.