Security Research Engineer, AI Safety and Security Engineering

NVIDIA, widely recognized as one of the world’s most desirable employers, believes open-weight models are foundational to American AI leadership, cybersecurity, and defense through broad scientific scrutiny. As part of this mission, our AI Safety & Security Engineering team builds and evaluates AI-powered tooling that finds, validates, and patches software vulnerabilities, recognizing that finding a bug is only the beginning. We are seeking a Security Research Engineer to advance our Validate and Patch capabilities by establishing what counts as a confirmed vulnerability and defining what constitutes a truly correct, safe fix. In this critical role, you will apply rigorous security judgment to well-defined categories of vulnerabilities. These affect NVIDIA-internal targets. You will turn complex analysis into repeatable methods that improve software people rely on daily.

Validation here requires meticulous care to confirm reports are real and reachable rather than noise, while patching requires ensuring fixes repair flaws, protect existing behavior, and hold up under strict revalidation. Working alongside harness and evaluation engineers, you will establish high engineering standards, document your reasoning for independent security reviews, and ensure your methods run reliably with fully traceable evidence. AI-assisted workflows are an integral part of this job, but so is maintaining a healthy, disciplined skepticism about their outputs. Beyond immediate fixes, your work will teach the entire program what trustworthy patching looks like while actively helping decide which vulnerability classes the team tackles next. Ultimately, we hold our results to an exceptionally high bar and value specific, verifiable proof of your technical expertise—such as CVEs, advisories, or original security tools—over polished phrasing.

What You'll Be Doing:

…