Nvidia Senior Security Architect - AI ML 

United States, Texas 

650021619

What you’ll be doing:

• Help define the field of ML/AI security architecture.

• Research, define, design, advise, develop, review, and implement architecture solutions meeting internal and external security requirements and standards.

• Collaborate across the company to guide the direction of designing secure AI and ML products, working with hardware, software, research, IT, and product teams.

• Architectural modeling, validation, definition, following standards bodies, and developing infrastructure enabling trusted platforms using hardware security methods.

• Perform Product Cybersecurity assessments on projects of multiple NVIDIA product lines. Complete independent reviews on project work packages that are AI and ML specific.

• Develop new attacks and defenses for ML/AI enabled applications.

• Support the development of the Product Cybersecurity Training strategy and deliver cybersecurity trainings to increase awareness and understanding of security requirements, tools, processes, and technical standards for NVIDIA ML/AI systems.

What we need to see:

• MS or PhD in Electrical Engineering, Computer Science, Computer Engineering, Artificial Intelligence, Data Science, Mathematics, Statistics, or equivalent experience.

• 8+ years of relevant work experience.

• First-hand work with Machine Learning, Deep-Learning, or Artificial Intelligence.

• Familiarity with current attacks on ML models, including adversarial examples, training data extraction, model extraction, and data poisoning.

• Background with attacks on and attack surface of LLM-powered systems, including direct and indirect prompt injection, guardrail evasion, and tool abuse.

• Experience using modern Deep Learning software architectures and frameworks like Jax or PyTorch

• Experience with security development lifecycle processes and tools

• Programming and debugging fundamentals across languages such as Python, C/C++

• Strong communication skills and a real passion for working as a team are essential

Ways to stand out from the crowd:

• Use of AI in vulnerability research or some other offensive domain

• Experience analyzing AI-generated code for security issues

• Demonstrated experience in MLops or Deep learning related infrastructure

• Understanding of data science, statistical analysis, and visualization

• Background of AI Trust principles and familiarity with application of ethical and safety perspectives to AI implementations