Senior AI Security Researcher
Core
Hands-on AI red teaming to reduce risks, threats, and vulnerabilities in NVIDIA networking AI products, models, systems, and infrastructure.
Role type
Senior IC AI security researcher (red team)
Builds
Tools and processes to expose novel weaknesses in AI models and systems
Domain
AI safety and security, Networking
Deliverable
production ML models
Required skills
AI safety and security research, offensive cybersecurity, LLM/MLLM/Generative AI/Agents/RAG workflows, Python programming, system design
Preferred skills
MLOps (Docker, Kubernetes), ML libraries (PyTorch, TensorRT, TensorRT-LLM)
Responsibilities
Drive hands-on safety and security research on AI and networking products; Develop tools to expose weaknesses in AI models; Partner with cross-functional teams to implement safety solutions; Act as technical focal point for AI safety and security expertise
Seniority
Senior, hands-on IC