Staff AI Security Architect

Quick Facts

• Role: Staff AI Security Architect (Security team)

• Focus: LLM-based features, agentic workflows, AI security architecture, threat modeling

• Collaboration: Engineering, Product, Data, IT, Legal, and GRC

• Travel: Occasional (up to 10–25%)

Description

You will lead threat modeling and security design reviews for LLM-based capabilities and agentic workflows, setting reference architectures and guardrails for safe AI development and adoption. You will translate evolving AI risk guidance into practical engineering standards, assess third-party model/vendor risks, and advise leaders on tradeoffs. This hands-on role requires strong AI/LLM security architecture skills and the ability to communicate complex AI risks to both technical and executive audiences.

Responsibilities

• Lead threat modeling and security design reviews for LLM features and agentic workflows

• Define reference architectures and guardrails for AI development and adoption

• Evaluate risks from third-party models and AI vendors

• Translate AI risk guidance into engineering standards and advise leaders on tradeoffs

• Influence cross-functionally without direct authority and communicate risk clearly

Requirements

• 8+ years of experience in security architecture, application security, or security engineering, including hands-on AI/ML or LLM application security

• Deep understanding of AI-specific threats and mitigations: prompt injection, data leakage, model and supply chain risk, insecure tool/plugin use, and excessive agent autonomy

• Proven experience leading threat modeling and security design reviews for complex systems and turning findings into actionable architecture requirements

• Strong cloud-native architecture experience on AWS, Azure, or GCP, including IAM, secrets management, data protection, and API security for AI workloads

• Experience designing AI guardrails and controls: input/output filtering, access control for retrieval and agent tools, logging/monitoring, and secure handling of sensitive customer data in AI pipelines

• Working knowledge of AI governance/risk frameworks such as NIST AI RMF and ISO/IEC 42001, and translating them into engineering requirements

• Ability to partner with Engineering and Product leaders, influence without authority, and communicate AI security risk to executive and non-technical audiences

Benefits

• Collaborative, fast-evolving AI security environment

• Growth opportunities, mentoring, and career development

• Inclusive and transparent hiring process and accommodation support