Senior Security Architect - AI and ML

at Nvidia
📍 Santa Clara, United States
USD 184,000-356,500 per year
SENIOR
✅ On-site

SCRAPED

Used Tools & Technologies

Not specified

Required Skills & Competences ?

Security @ 4 Python @ 4 Statistics @ 4 Machine Learning @ 4 MLOps @ 4 Data Science @ 4 Hiring @ 4 Communication @ 7 Mathematics @ 4 Debugging @ 4 LLM @ 4 PyTorch @ 4

Details

NVIDIA is seeking a technical leader to define, craft, implement, review, advise, and guide implementation of secure architectures for NVIDIA Artificial Intelligence (AI) / Machine Learning (ML) products, including Trusted Execution Environment architecture and other security architectures across the NVIDIA product line. You will take a strong hands-on role, working with diverse teams across NVIDIA and with external partners to define and meet security requirements for our innovative AI and ML projects. Opportunities include collaborating with technologies like NeMo, NeMo-Guardrails, BioNeMo, Morpheus, and Omniverse.

Responsibilities

  • 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 (hardware, software, research, IT, and product teams) to guide the direction of designing secure AI and ML products.
  • Perform architectural modeling, validation, and definition; follow standards bodies; develop infrastructure enabling trusted platforms using hardware security methods.
  • Perform Product Cybersecurity assessments on projects across multiple NVIDIA product lines and complete independent reviews on AI/ML-specific project work packages.
  • Develop new attacks and defenses for ML/AI-enabled applications.
  • Support the development and delivery of Product Cybersecurity Training to increase awareness and understanding of security requirements, tools, processes, and technical standards for NVIDIA ML/AI systems.

Requirements

  • 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 and C/C++.
  • Strong communication skills and a passion for working as a team.

Ways to stand out

  • Use of AI in vulnerability research or other offensive domains.
  • 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 in AI trust principles and familiarity with applying ethical and safety perspectives to AI implementations.

Benefits & Compensation

  • Base salary range (determined by location, experience, and peer pay):
    • Level 4: 184,000 USD - 287,500 USD
    • Level 5: 224,000 USD - 356,500 USD
  • Eligibility for equity and additional benefits (link provided in original posting).

Additional details

  • Location: Santa Clara, CA, United States (on-site expected per listing).
  • Employment type: Full time.
  • Applications accepted at least until August 8, 2025.
  • NVIDIA is an equal opportunity employer and emphasizes diversity and inclusion in hiring and promotion practices.