Senior Research Scientist - AI Security

NVIDIA•Seattle, WA

About The Position

NVIDIA’s Agentic Cybersecurity Research team is seeking an AI security researcher to develop research and technology that protects AI models, systems, and infrastructure, and uses AI to secure systems. The work spans using models and agents to improve cybersecurity and securing models and agents. The researcher will investigate new problems at the intersection of AI and security, develop tools and processes to identify or remediate weaknesses in conventional and AI systems, and share research results through peer-reviewed publications and with security, machine learning, business, and internal teams.

Requirements

Master’s or PhD degree in Computer Science, Computer Engineering, Data Science, or a related field, or equivalent experience.
At least 5 years of experience in machine learning, cybersecurity, or closely related fields.
Demonstrated programming expertise.
Outstanding knowledge of AI and conventional software weaknesses and mitigation strategies.
In-depth understanding of Generative AI workflows.
Self-starter with enthusiasm for growth, continuous learning, and sharing findings.
Motivation and curiosity about new technologies.
Ability to clearly present sophisticated technical information.

Nice To Haves

Strong collaboration skills and a history of successful cross-functional projects.
Experience discovering CVEs or building successful tooling.
Knowledge of adversarial machine learning and techniques for defending against adversarial techniques.
Experience with secure software development practices.
Ability to build human-friendly resources.

Responsibilities

Conduct novel research to improve cybersecurity and AI, including work on using models and agents for cybersecurity and securing models and agents.
Contribute research on new problems in AI and security.
Develop tools and processes to expose or remediate novel weaknesses in conventional and AI systems.
Present findings through peer-reviewed publications or other communications with security, machine learning, and business communities.
Share results with teams across NVIDIA and apply them to relevant problems in a range of contexts.