The opportunity
The Guardian team builds practical safety and oversight systems for increasingly capable AI agents. Our goal is to make it possible for agents to take on longer-running, higher-autonomy work while preserving meaningful safeguards, respecting user intent, and intervening when…
What you'll do
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.
What they're looking for
- 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.