AI Staff Security Engineer

Overview

In this role you establish and advance a proactive security stance for AI-driven platforms. You will design and operationalize automated security workflows and govern AI tooling to minimize risk across the enterprise. You’ll defend proprietary models against sophisticated threats and lead governance aligned with industry frameworks. This position combines hands-on security engineering with cross-functional collaboration to shape secure AI development and deployment at scale.

Responsibilities

• Augment vulnerability management to focus on AI-centric risks and supply chain threats, prioritizing critical legacy infrastructure
• Design and deploy AI Detection and Response (AIDR) solutions to protect models against prompt injection, data poisoning, and model inversion/extraction
• Automate security workflows through Agentic/SIEM integrations to enable rapid response to autonomous adversary AI
• Conduct offensive security operations including AI Red Teaming and penetration testing of generative and agentic systems
• Lead Shadow AI defense by building AI access governance tools and enforcing tool review processes
• Drive security compliance and AI governance using frameworks like Google’s SAIF and CSA’s AICM with emphasis on GDPR/PII and ethical AI
• Embed secure-by-design principles into the CI/CD for AI systems, with testing coverage pre and post deployment
• Communicate complex security concepts to non-technical audiences to raise security awareness across the organization

Key requirements

• Offensive security experience including AI Red Teaming/Penetration Testing against agentic frameworks and LLM integrations
• Experience deploying AI Detection and Response (AIDR) workflows with agentic and SIEM technologies and AI-native threat modeling (MAESTRO)
• Understanding of Governance, Risk, and Compliance (GRC), particularly AI governance and least-privilege for human and AI identities
• Upper-Intermediate English fluency for effective communication
• Strong presentation skills to translate security data for non-technical stakeholders
• Ability to work across time zones (EST/PST) for cross-functional collaboration
• Self-directed mindset focused on innovative, modern security solutions

• Strong communication and presentation abilities
• Cross-functional collaboration
• Proactive problem solving
• AI security and threat modeling (MAESTRO)
• AI Detection and Response (AIDR)
• Agentic and SIEM integration

…