Security Research Engineer, AI Safety and Security Engineering
About The Position
NVIDIA’s AI Safety & Security Engineering team builds and evaluates AI-powered tools to find, validate, and patch software vulnerabilities. The Security Research Engineer will advance the team’s Validate and Patch capabilities by defining when a vulnerability is confirmed and what constitutes a correct, safe fix. The work focuses on well-defined vulnerability categories affecting NVIDIA-internal targets and turns complex security analysis into repeatable methods. The role requires carefully validating that reported vulnerabilities are real and reachable, and verifying that fixes address the flaw, preserve existing behavior, and pass strict revalidation. Working with harness and evaluation engineers, the engineer will establish high engineering standards, document reasoning for independent security reviews, and ensure methods run reliably with traceable evidence. AI-assisted workflows are integral, alongside disciplined evaluation of their outputs. The engineer will also help guide which vulnerability classes the team addresses and contribute evidence of technical expertise, such as CVEs, advisories, or original security tools.
Requirements
- Bachelor’s degree or equivalent experience.
- 12+ years in security research or software engineering.
- Hands-on experience with vulnerability research, fuzzing, program analysis, or secure development in C, C++, or Python.
- Rigor in determining whether a fix is correct and safe, including regression prevention and behavior preservation.
- Comfort using AI-assisted tools for analysis and development.
Nice To Haves
- Public vulnerability research, such as CVEs, advisories, or publications.
- Experience building or extending fuzzers, static analyzers, or symbolic-execution tools.
- Familiarity with LLM-based coding or analysis agents.
Responsibilities
- Develop techniques to confirm that vulnerabilities are real and reachable.
- Advance approaches for generating and verifying safe fixes.
- Define correctness, regression, and revalidation standards with reviewers.
- Research bounded vulnerability classes against NVIDIA-internal targets.
- Document security reasoning for independent reviews and ensure methods provide traceable evidence.
- Help determine which vulnerability classes the team tackles next.
Benefits
- Equity
- Benefits package
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
