Software Engineer, Guardian

Highlights

• Build oversight systems letting agents handle longer, higher-autonomy work safely.
• Design real-time Auto-review that evaluates risky agent actions in context.
• Integrate Guardian safety capabilities across OpenAI agent products.

Ideal candidate

Product-minded engineer who ships reliable production systems and thrives in ambiguity. You enjoy partnering with researchers and care deeply about making AI agents useful, trustworthy, and safe.

Requirements

• Experience building and shipping complex production software with ownership across design, implementation, deployment, and operation
• Built with AI agents or large language models in a core product, startup, or serious independent project
• Strong software engineering fundamentals with ability to design reliable backend services, APIs, and infrastructure
• Sound product-engineering judgment navigating tradeoffs across safety, usability, speed, and reliability
• Enjoy partnering with researchers to translate open-ended ideas into practical systems using experiments and evaluations
• Comfortable with ambiguity, takes initiative, and communicates clearly across technical disciplines
• Care deeply about building AI systems that are useful, trustworthy, and safe