AI Security Architect for Secure ML/LLM Systems

ACV Auctions; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

ACV Auctions is seeking a Principal Architect, Product Security to define target-state secure architecture for AI/ML systems and oversee secure design across engineering. You will own security controls for AI-assisted development, guarding against adversarial inputs while enabling developer velocity.

The role requires deep GenAI/LLM security experience, hands-on coding, and the ability to translate policy into enforceable technical controls.

Qualifications

• Bachelor's degree or commensurate experience with security focus
• 12+ years' of security experience, 15+ years without degree
• Hands-on GenAI/LLM security work demonstrated by production or verifiable work
• 2+ years of production AI security experience preferred
• Security architecture ownership for AI systems and applications
• Knowledge of OWASP Top 10 for LLM/Agentic Applications and MITRE ATLAS

Responsibilities

• Define target-state secure architecture for AI/ML systems and reference patterns
• Protect integrity of vision-based condition and pricing pipelines against adversarial inputs
• Set secure-by-default standards adopted across engineering for AI development
• Threat model and review high-risk AI and application designs
• Stand up AI security testing capability including adversarial testing and red-teaming
• Advise on multi-year AI security strategy and translate policy into technical controls
• Scale AI security expertise across engineering and mentor senior engineers
• Represent ACV's AI security architecture externally

Skills

AI security

Security architecture

Threat modeling

Cloud security

Python coding

Security tooling

Education

Bachelor's degree or commensurate experience

Tools

Garak

PyRIT

promptfoo

Job description

ACV Auctions is seeking a Principal Architect, Product Security to define target-state secure architecture for AI/ML systems and oversee secure design across engineering. You will own security controls for AI-assisted development, guarding against adversarial inputs while enabling developer velocity.

The role requires deep GenAI/LLM security experience, hands-on coding, and the ability to translate policy into enforceable technical controls.