Senior AI Safety Red Teamer

We are looking for an outstanding technical AI red teamer with hands-on safety and security experience to help us improve the safety posture of AI models, systems and infrastructure. In this role you will reduce risk, threats, and vulnerabilities in NVIDIA networking AI products.

Your key responsibilities will include:

• Drive hands-on safety and security research on a range of AI and networking products.
• Develop tools and processes to expose novel weaknesses in AI models and systems to preempt threats.
• Participate in defining and ensuring AI development processes meet safety and security standards.
• Partner with cross-functional teams to understand needs and implement solutions.
• Be a technical focal point across multiple teams and provide hands-on AI safety, security and engineering expertise.

To succeed in this role, you will need:

• A Bachelor’s or Master’s Degree in Computer Science, Computer Engineering, Data Science, or a related field (or equivalent experience).
• Demonstrated experience of 5+ years in AI safety/security and offensive cybersecurity.
• Knowledge of AI (both model and infrastructure) vulnerabilities and effective mitigation strategies.
• In-depth understanding of LLM, MLOps, Generative AI, Agents and RAG workflows.
• Proven Python programming expertise.
• Self-starter with a passion for growth, enthusiasm for continuous learning, and sharing findings across the team.
• Extremely motivated, highly passionate, and curious about new technologies.

If you have hands-on experience designing and building software products, including infrastructure and system design, knowledge of MLOps technologies such as Docker and Kubernetes, and familiarity with ML libraries (PyTorch, TensorRT, or TensorRT-LLM), you will stand out from the crowd.