AI Agent Security Architect

We are looking for an AI Agent Security Architect to function as the primary technical authority for Replit’s autonomous and AI agent security blueprint. In this critical role, you will design, implement, and maintain the runtime defense systems, guardrail frameworks, and sandboxing architectures that govern AI agents executing code, invoking tools, and reasoning across our platform. You will be a key technical contributor—leading high-impact AI security initiatives and bridging the gap between non-deterministic AI behavior and rigorous cybersecurity controls for both engineering and executive leadership.

• AI Agent Security Strategy & Technical Execution
• AI Agent Security Blueprint: 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.
• Runtime Guardrails & Policy Enforcement: 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.
• Agent Execution & Tool Sandboxing: Partner with Infrastructure and AppSec teams to design secure, short-lived, micro-isolated environments (e.g., microVMs, WebAssembly, container sandboxes) where agents can dynamically execute code, run shell commands, and interact with host operating systems safely.
• Agentic Threat Modeling & Red Teaming: 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.
• Identity, Delegation & Least Privilege: Architect fine-grained permission models and step-up Human-in-the-Loop (HITL) authorization patterns for agents acting on behalf of users—ensuring agents never exceed the delegated privileges of the end user or misuse API keys.
• Context & Memory Boundary Security: Design strict data isolation and poisoning prevention controls for vector databases, retrieval-augmented generation (RAG) pipelines, and long-term conversation memories across multi-tenant workloads.
• Risk Management & Cross-Functional Enablement
• Maintain the AI Security Source of Truth: Define, document, and maintain authoritative secure design patterns and SDKs for engineering teams building internal or customer-facing AI agent capabilities.
• Contribution to Risk Register: Identify, quantify, and document non-deterministic and agentic security risks (e.g., OWASP Top 10 for LLMs & AI Agents, MITRE ATLAS), ensuring they are accurately represented in the Cybersecurity Risk Register.
• Auditability & Observability: Design tamper-evident logging and telemetry standards for agent reasoning chains, tool execution history, and context assembly to support incident response, forensics, and GRC requirements.
• Compliance & Sales Enablement: Partner with GRC to translate complex AI security controls into enterprise-ready audit documentation (e.g., ISO 42001, NIST AI RMF, EU AI Act readiness) and support Sales on complex enterprise security inquiries regarding AI safety.