Senior AI Security Research Scientist: AI Safety & Defense

NVIDIA Corporation; Seattle (WA); On-site; USD 192,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking an AI Security Researcher for the Agentic Cybersecurity Research team in Seattle. You will conduct novel research to protect AI models, systems, and infrastructure using AI, with emphasis on securing both models and agents.

Requirements include a master's or PhD in a related field or equivalent experience, 5+ years in ML or cybersecurity, strong programming skills, and deep knowledge of AI weaknesses and mitigations, including Generative AI workflows.

Qualifications

• Master's or PhD in Computer Science, Computer Engineering, Data Science, or a related field (or equivalent experience).
• 5+ years in machine learning, cybersecurity, or closely related fields.
• Shown programming expertise.
• Outstanding knowledge of AI and conventional software weaknesses and mitigation strategies.
• In-depth understanding of Generative AI workflows.

Responsibilities

• Novel and creative research on improving cybersecurity and AI.
• Focus on using models and agents to improve cybersecurity, and securing models and agents.
• Contribute research on new and exciting problems in AI and security.
• Develop tools and processes to expose or remediate weaknesses in conventional and AI systems.
• Present results by publishing in peer-reviewed venues or sharing with security, ML, and business communities.
• Improve AI and security at NVIDIA by sharing results with other teams.

Skills

Machine learning

Cybersecurity

Programming

Generative AI

Education

Master's or PhD in CS/CE/Data Science or related

Tools

Python

PyTorch

TensorFlow

Job description

NVIDIA is seeking an AI Security Researcher for the Agentic Cybersecurity Research team in Seattle. You will conduct novel research to protect AI models, systems, and infrastructure using AI, with emphasis on securing both models and agents.

Requirements include a master's or PhD in a related field or equivalent experience, 5+ years in ML or cybersecurity, strong programming skills, and deep knowledge of AI weaknesses and mitigations, including Generative AI workflows.