• Design, build, and operate core components of Auto-review and the broader Guardian platform, balancing safety, product utility, latency, and operational reliability.
• Build production systems that evaluate agent actions in real time, detect potentially harmful behavior, and support safe recovery or escalation paths.
• Improve how oversight systems understand user intent, environmental context, permissions, and relevant personalization signals while protecting privacy and avoiding unnecessary friction.
• Partner closely with alignment researchers to turn prototypes, evaluations, and new monitoring techniques into scalable product capabilities.
• Work across Product, Security, Infrastructure, and other engineering teams to integrate Guardian capabilities into agent experiences throughout OpenAI.
• Develop evaluations, adversarial tests, and monitoring to understand safety performance, false positives, latency, and user impact.
• Own projects end to end, contribute to technical direction and design reviews, and investigate failures to improve system behavior and reliability.
• Have experience building and shipping complex production software, with ownership across design, implementation, deployment, and operation.
• Have built with AI agents or large language models in a core product, startup, or technically serious independent project, and understand the unique challenges of agentic systems.
• Bring strong software engineering fundamentals and can design reliable backend services, APIs, and infrastructure.
• Exercise sound product-engineering judgment and can navigate tradeoffs across safety, usability, speed, and reliability.
• Enjoy working closely with researchers, translating open-ended ideas into practical systems, and using experiments and evaluations to guide decisions.
• Are comfortable with ambiguity, take initiative, and communicate clearly across technical disciplines.
• Care deeply about building AI systems that are useful, trustworthy, and safe.