The opportunity
We build software that helps understand and reduce risks from increasingly capable AI systems. Our work spans cybersecurity, frontier-risk evaluations, and red teaming, with a focus on turning research and testing into practical tools and reliable systems.
What you'll do
Design, build, and maintain software that supports cybersecurity research,: frontier-risk evaluations, and red teaming.
Develop tools and workflows that make it easier to run evaluations, inspect results, and investigate failures.
Build services, APIs, data pipelines, and interfaces that help researchers work efficiently.
Turn experimental workflows into reusable, well-tested, and documented systems.
Own projects from understanding the problem and designing a solution through: implementation, deployment, and ongoing operation.
Improve reliability, performance, observability, security, and usability as needs evolve.
What they're looking for
- Collaborate with researchers, security specialists, and engineers to identify: useful problems and make practical technical decisions.
- Have strong software engineering fundamentals and experience building,: shipping, and maintaining production software.
- Are proficient in a general-purpose programming language and comfortable: learning unfamiliar tools and systems.
- Have experience in one or more areas such as backend development, full-stack: applications, infrastructure, or data systems.
