Senior Research Scientist - AI Security
Overview:
Please make sure you read the following details carefully before making any applications. Join NVIDIA’s Agentic Cybersecurity Research team as an AI Security Researcher to advance protection for AI models, systems, and infrastructure. You will conduct novel research in AI security, develop tools to expose and remediate weaknesses, and share findings with cross-functional teams and the broader community. This role combines hands-on security work with cutting-edge AI, positioned to shape secure AI at scale. You’ll engage with peers to address meaningful challenges and contribute to NVIDIA’s leadership in secure AI.Compensation / Benefitsequitybenefitsbase salary rangeremote/work flexibilitycareer growth opportunitiesinclusive environment
Responsibilities:
- Conduct novel research on cybersecurity and AI, focusing on securing models and agents as well as using models/agents to enhance cybersecurity
- Develop tools and processes to expose or remediate weaknesses in conventional and AI systems
- Publish results in peer‑reviewed venues and communicate findings to security, ML, and business communities
- Share results across NVIDIA to improve AI and security and solve cross‑context problems
- Collaborate with cross‑functional teams to apply research to real-world NVIDIA systems
Key requirements:
- Master’s or PhD in CS, CE, data science, or related field (or equivalent experience)5+ years in machine learning, cybersecurity, or related fields
- Proven programming expertise
- Outstanding knowledge of AI and conventional software weaknesses xaygatp and mitigation strategies
- In-depth understanding of Generative AI workflows
- Self-starter with passion for growth and continuous learning
- Motivated and curious about new technologies
- Ability to present sophisticated technical information clearly
- Cross‑functional collaboration
- Strong communication of complex ideas
- Curiosity and drive for learning
- Generative AI workflows
- Adversarial machine learning and defenses
- Secure software development practices