AI Agent Security Architect

Join Replit as an AI Agent Security Architect, where you will be the primary technical authority for our autonomous and AI agent security blueprint. In this critical role, you will design, implement, and maintain runtime defense systems, guardrail frameworks, and sandboxing architectures. You will lead high-impact AI security initiatives and bridge the gap between non-deterministic AI behavior and rigorous cybersecurity controls. This is a remote-first position with flexible work hours and a comprehensive benefits package.

• Define the long-term vision and architectural patterns for securing autonomous agent workflows, Model Context Protocol (MCP) integrations, multi-turn reasoning loops, and multi-agent coordination.
• Architect and deploy dynamic input/output guardrail systems, semantic firewalls, and real-time intent verification filters to prevent goal hijacking, system prompt leaks, and indirect prompt injections.
• Conduct specialized threat modeling against non-deterministic systems. Lead automated and manual AI red-teaming initiatives to uncover vulnerabilities in RAG context pipelines, vector stores, and tool-calling interfaces.

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