Staff Security Engineer (Offensive AI)

Join our team as a Staff Security Engineer (Offensive AI) and be at the forefront of cutting-edge technology. You will conduct original offensive research against our innovative browser, Dia, and its various components. Your work will involve threat modeling, automated vulnerability discovery, and collaborating with engineers on remediation. You will have the opportunity to shape the future of security testing and contribute to the development of new tools and systems. Enjoy a flexible work environment, competitive compensation, and comprehensive benefits.

• Conduct original offensive research against Dia, focusing on various attack vectors and vulnerabilities.
• Design and build automated vulnerability discovery systems, including model-driven scanning and fuzzing.
• Collaborate with engineers to eliminate entire classes of bugs and set the standard for security testing before features ship.

• You resonate with our company values
• You thrive in a high-trust, high-ambiguity environment: you seek feedback, but you don't need hand-holding
• You write findings engineers act on, and you can stay in the fix conversation and push for the durable version without owning the remediation yourself
• Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest
• You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You'd rather build the thing that finds a bug a thousand times than find it once
• We're primarily focused on hiring in North American time zones and require that folks have 4+ hours of overlap time with team members in Eastern Time Zone
• Practical fluency using LLMs as instruments, not just as targets, plus a working sense of when their output is noise
• 8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed