AI Security Research Scientist — Innovate Safe AI Systems

Remote Jobs; Seattle (WA); On-site; USD 168,000 - 305,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA's Agentic Cybersecurity Research team is seeking an AI Security Researcher to advance protection of AI models, systems and infrastructure in Seattle, WA. You will do hands-on safety research and develop defenses that scale across environments.

Candidates have a Master’s or PhD in CS/CE/DS (or equivalent), 5+ years in ML or cybersecurity, strong programming skills, and deep knowledge of AI weaknesses and Generative AI workflows. Equity and benefits accompany the role.

Qualifications

• Master's or PhD in Computer Science, Computer Engineering, Data Science, or related field (or equivalent).
• 5+ years in machine learning, cybersecurity, or related fields.
• Strong programming skills and knowledge of AI weaknesses and mitigation strategies.
• Deep understanding of Generative AI workflows.
• Self-starter with enthusiasm for learning and sharing findings.
• Ability to present sophisticated technical information clearly.

Responsibilities

• Conduct novel and creative research on cybersecurity and AI for secure systems.
• Develop tools and processes to expose or remediate weaknesses in AI and conventional systems.
• Publish results in peer‑reviewed venues or share with security and ML communities.
• Collaborate across teams to improve NVIDIA security posture and tooling.
• Present findings and drive adoption of secure AI practices within the company.

Skills

Machine learning

Cybersecurity

Generative AI

Programming

AI safety

Communication

Education

Master's or PhD in CS/CE/DS

Tools

Python

AI/ML frameworks

Penetration testing tools

Job description

NVIDIA's Agentic Cybersecurity Research team is seeking an AI Security Researcher to advance protection of AI models, systems and infrastructure in Seattle, WA. You will do hands-on safety research and develop defenses that scale across environments.

Candidates have a Master’s or PhD in CS/CE/DS (or equivalent), 5+ years in ML or cybersecurity, strong programming skills, and deep knowledge of AI weaknesses and Generative AI workflows. Equity and benefits accompany the role.