Senior Manager, AI Runtime Security

Vanguard•Malvern, PA

1d•Hybrid

About The Position

Build and lead a team of engineers and analysts focused on AI runtime protection and operational AI security controls. Define and execute strategy for AI runtime security, including guardrails, behavioral attestation, and rogue agent detection. Operationalize AI runtime controls across AI gateways, APIs, and production environments. Partner with IT, platform engineering, and cybersecurity teams to integrate detection, response, containment, and kill-switch capabilities. Build scalable security operations processes to enforce AI runtime protections in real time across deployed AI systems. Drive integration of runtime telemetry into enterprise monitoring and incident response workflows. Establish security standards and best practices for securing AI-enabled applications and agentic systems. Collaborate across architecture, cloud, and engineering teams to embed AI security controls into enterprise platforms.

Requirements

10+ years of experience securing endpoints, cloud platforms and SaaS environments
Deep experience with AWS, Azure, and/or Google Cloud Platform (GCP) security architectures
Experience leading security engineering or cyber operations teams in enterprise environments
Strong understanding of AI systems, AI runtime controls, and modern AI security risks
Familiarity with AI guardrails, AI gateways, behavioral monitoring, and runtime enforcement technologies
Experience integrating security controls into production platforms and operational workflows
Strong communication and stakeholder management skills with the ability to influence cross-functional teams

Nice To Haves

Certifications such as: CCSP AWS Certified Solutions Architect – Associate Google Associate Cloud Engineer
Experience securing AI/ML platforms, autonomous agents, or generative AI systems
Familiarity with real-time detection and response capabilities for AI-enabled environments

Responsibilities

Build and lead a team of engineers and analysts focused on AI runtime protection and operational AI security controls
Define and execute strategy for AI runtime security, including guardrails, behavioral attestation, and rogue agent agent detection
Operationalize AI runtime controls across AI gateways, APIs, and production environments
Partner with IT, platform engineering, and cybersecurity teams to integrate detection, response, containment, and kill-switch capabilities
Build scalable security operations processes to enforce AI runtime protections in real time across deployed AI systems
Drive integration of runtime telemetry into enterprise monitoring and incident response workflows
Establish security standards and best practices for securing AI-enabled applications and agentic systems
Collaborate across architecture, cloud, and engineering teams to embed AI security controls into enterprise platforms