Software Engineer, Guardian
AI research and deployment company building and deploying frontier AI products, including ChatGPT, Codex, and its API platform.
Projects
About OpenAI
OpenAI’s mission is to ensure artificial general intelligence benefits all of humanity. It consists of the nonprofit OpenAI Foundation and OpenAI Group, a public benefit corporation governed by the Foundation.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and build production systems that evaluate agent behavior, identify risk and take appropriate action without adding unnecessary friction. You will work across architecture, implementation, evaluation and operations, partnering with alignment researchers and product, security and infrastructure teams. The role is based in the London office.
Requirements
- Experience building and shipping complex production software
- Experience building with AI agents or large language models
- Strong software engineering fundamentals for backend services, APIs and infrastructure
- Sound product-engineering judgment
- Clear communication across technical disciplines
Responsibilities
- Design, build and operate core components of Auto-review and the Guardian platform
- Build production systems that evaluate agent actions in real time and detect harmful behavior
- Improve how oversight systems understand user intent, context, permissions and personalization signals
- Partner with alignment researchers to turn prototypes into scalable capabilities
- Work across Product, Security and Infrastructure to integrate Guardian capabilities
- Develop evaluations, adversarial tests and monitoring
- Own projects end to end and investigate failures
