Agentic Security Engineer
Core
Translate security requirements into runtime enforcement mechanisms for agentic AI systems, focusing on orchestration frameworks, APIs, and external tools.
Role type
Senior IC agentic security engineer
Builds
Secure agentic AI deployments, runtime enforcement controls, and monitoring systems for AI agent activity
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models | infrastructure
Required skills
Runtime security, policy enforcement, action validation, execution tracing, API security, IAM, observability, logging, monitoring, prompt injection mitigation, tool execution security, memory poisoning prevention, context manipulation defense, NIST AI RMF compliance, OWASP Top 10 for LLM Applications, MITRE ATLAS
Preferred skills
Advanced degrees in AI/ML or cybersecurity, AI/ML or cybersecurity certifications
Technologies
AWS, Azure, AI/ML platforms, orchestration frameworks, MCP servers
Responsibilities
Assess security of agentic AI systems, orchestration frameworks, and enterprise integrations; Build execution tracing and monitoring for AI agent activity; Implement controls for autonomous decision-making and delegated authority; Collaborate with AI engineering and platform teams on secure deployment; Support detection and investigation of unsafe AI runtime behavior.