AI Agent Security Architect

About the job

Responsibilities

• Define the architectural vision and patterns for securing autonomous agent workflows, MCP integrations, multi-turn reasoning, and multi-agent coordination.
• Architect and deploy dynamic guardrail systems, semantic firewalls, and intent verification filters to prevent prompt injection and goal hijacking.
• Design secure, isolated environments (e.g., microVMs, WebAssembly) for agents to safely execute code and interact with host systems.
• Conduct specialized threat modeling and lead AI red-teaming initiatives to identify vulnerabilities in RAG pipelines, vector stores, and tool-calling interfaces.
• Architect fine-grained permission models and human-in-the-loop authorization for agents acting on behalf of users.
• Design data isolation and poisoning prevention controls for vector databases, RAG pipelines, and conversation memories.
• Define, document, and maintain secure design patterns and SDKs for AI agent development.
• Identify, quantify, and document agentic security risks and contribute to the Cybersecurity Risk Register.
• Design logging and telemetry standards for agent reasoning and tool execution to support incident response.
• Partner with GRC to translate AI security controls into audit documentation and support sales inquiries on AI safety.

Requirements

• 6+ years of experience in security engineering or architecture, with at least 2 years focused on AI/ML security, LLM application security, or agentic frameworks.
• Deep understanding of agentic architectures and protocols (e.g., MCP, LangChain, AutoGen, CrewAI, ReAct, vector databases).
• Hands-on expertise with agentic AI threat vectors (e.g., Indirect Prompt Injection, Goal Hijacking, Tool Parameter Tampering, Data Poisoning, Context Contamination).
• Strong background in safety standards and risk frameworks (e.g., OWASP Top 10 for LLMs & AI Agents, NIST AI RMF, MITRE ATLAS).
• Proficiency in Python, Go, or TypeScript/JavaScript with experience in code review and building security tooling.
• Experience authoring, maintaining, and evangelizing technical security architecture documentation.
• Exceptional ability to communicate complex AI risks to technical and executive stakeholders.
• Proven track record of contributing to an enterprise Cybersecurity Risk Register.
• Experience designing runtime sandboxing and isolation technologies (e.g., Firecracker, gVisor, Docker, WebAssembly) is a plus.

Benefits

• Competitive Salary & Equity
• 401(k) Program with a 4% match (US Only)
• Health, Dental, Vision and Life Insurance
• Short Term and Long Term Disability
• Paid Parental, Medical, Caregiver Leave
• Flexible Time Off (FTO) + Holidays
• Commuter Benefits (In-Office & US Only)
• Monthly Wellness Stipend
• Autonomous Work Environment
• In Office Set-Up Reimbursement (In-Office Only)
• Quarterly Team Gatherings
• In Office Amenities (In-Office Only)