About The Position

NVIDIA is seeking a Security Research Engineer to join its AI Safety & Security Engineering team. This role focuses on advancing AI-powered tooling for finding, validating, and patching software vulnerabilities, with a specific emphasis on establishing criteria for confirmed vulnerabilities and correct, safe fixes. The engineer will apply rigorous security judgment to well-defined categories of vulnerabilities affecting NVIDIA-internal targets, transforming complex analysis into repeatable methods. Key aspects include meticulous validation to confirm reports, ensuring fixes repair flaws, protect existing behavior, and withstand revalidation. The role involves working with harness and evaluation engineers, establishing high engineering standards, documenting reasoning for security reviews, and ensuring methods run reliably with traceable evidence. While AI-assisted workflows are integral, a disciplined skepticism towards their outputs is also crucial. The work will inform the entire program on trustworthy patching and help decide future vulnerability class targets. NVIDIA holds its results to an exceptionally high bar, valuing specific, verifiable proof of technical expertise over polished phrasing.

Requirements

  • Bachelor's degree (or equivalent experience) with 5+ years in security research or software engineering.
  • Hands-on vulnerability research, fuzzing, program analysis, or secure development in C, C++, or Python.
  • Rigor about what makes a fix correct and safe, including regression and behavior preservation.
  • Comfort using AI-assisted tools for analysis and development.

Nice To Haves

  • CVEs, advisories, or publications in vulnerability research.
  • Experience building or extending fuzzers, static analyzers, or symbolic-execution tools.
  • Familiarity with LLM-based coding or analysis agents.

Responsibilities

  • Develop techniques that confirm vulnerabilities are real and reachable.
  • Advance approaches for generating and verifying safe fixes.
  • Define correctness, regression, and revalidation standards with reviewers.
  • Work bounded vulnerability classes against internal targets.

Benefits

  • Competitive salaries
  • Generous benefits package
  • Equity
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service