Agent Security Engineer
Core
Design guardrails, attack systems, and build governance controls to secure autonomous AI agents before and after production.
Role type
Security engineer specializing in autonomous AI agents
Builds
Governance controls and security guardrails for AI agents
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
LLM attack techniques, identity and access controls, agent frameworks, Python, cloud security, policy-as-code
Preferred skills
offensive security, risk communication
Technologies
LangGraph, OpenAI Agents SDK, CrewAI, Model Context Protocol, OAuth 2.0, OIDC, OPA, Cedar, AWS, Azure, GCP
Responsibilities
Design guardrails for autonomous AI agents, perform security testing on agent systems, build governance controls for agent deployment
Seniority
Mid-Senior, hands-on IC
