Senior AI Security Engineer

NVIDIA is seeking a Senior AI Security Engineer for its Agentic & AI Cybersecurity Research team. The role develops practical cybersecurity software for AI, turns research code into product prototypes, and builds tools and services that help teams adopt secure agent approaches.

Responsibilities:

• Building leading software ahead of the curve to accelerate and improve cybersecurity tooling for AI
• Collaborating closely with research teams and product teams to be responsible for development of research code into alpha versions of products
• Rapidly identifying the highest-value MVP for ambiguous security and identity problems, prototyping solutions, validating them with partner teams, and iterating towards production-ready services
• Developing reusable skills, CLI tools, APIs, and integration patterns to help internal teams embrace secure agent approaches across enterprise tools and platforms
• Partnering closely with teams across Enterprise Security, Product Security, Enterprise AI, Enterprise Product, and relevant platform teams to align architecture with real workflow needs and operational constraints

Requirements:

• Bachelor's degree or Master's degree or equivalent experience in Computer Science or a related field
• 8+ years in software engineering, security engineering, or related areas, including hands-on technical leadership
• Excellent software engineering skills, including crafting and building backend services, APIs, automation, or platform components in various programming environments. The role requires quickly learning new paradigms, frameworks, and tools as needed
• Experience with multi-contributor software projects and long-running software projects
• Familiarity with building agents, AI tooling, and architectures
• Track record of framing problem spaces, defining an MVP, prototyping quickly, and evolving ideas into production systems
• Familiarity with offensive security, adversarial thinking, red teaming, or attack-path analysis, capable of applying that perspective to architecture decisions and security tradeoffs
• Flexibility and willingness to frequently collaborate across organizational boundaries, balancing security with usability and adoption
• Demonstrate strong human-centered thinking, carefully integrating underlying requirements from researchers and users into code
• Excellent software engineering instincts, including the ability to build reusable frameworks, understand and refine requirements, build tooling that improve engineering velocity and consistency
• Deep familiarity with open-source projects, including community involvement, workflow, and governance
• Experience with agentic or AI-adjacent systems, such as tool-using applications, workflow orchestration, evaluation loops, policy controls, memory/context services, or trust and discovery systems
• Understanding of AI-specific security risks such as injection, tool misuse, unauthorized access expansion, data exfiltration, or unsafe delegation patterns