Job Description:

We are seeking a versatile and senior AI Staff Security Engineer to serve as the linchpin of our security posture. You will be responsible for moving our organization toward a highly proactive security stance by engineering automated workflows that replace manual overhead.

This role will be critical in managing the systemic risk of Shadow AI agentic frameworks and enforcing the principle of least privilege by leveraging configuration management to programmatically control software across the enterprise. You will secure our core AI-driven platforms and protect them from advanced threats.

• Augment the complete vulnerability management lifecycle to prioritize AI-centric risks, including supply chain attacks using tools for SBOM tracking, and targeting critical unpatched legacy infrastructure.
• Design, deploy, and operationalize AI Detection and Response (AIDR) solutions to protect proprietary models and systems from novel threats like prompt injection, data poisoning, and model inversion/extraction.
• Automate critical security workflows using Agentic/SIEM integration to achieve high operational velocity and enable rapid response to millisecond attack speeds generated by autonomous adversary AI.
• Execute regular offensive security operations, including AI Red Teaming and penetration testing of generative and agentic systems.
• Lead the defense against Shadow AI by developing and deploying AI access governance tools and enforcing strict adherence to our review process for all new tools.
• Drive security compliance and AI governance by aligning systems with frameworks like Google's SAIF and CSA's AICM, focusing on data privacy (GDPR/PII) and ethical AI principles.
• Enforce secure-by-design principles and integrate security checks into the continuous AI development lifecycle (CI/CD), ensuring coverage for all AI system testing pre and post-deployment.
• Present complex security concepts (e.g., prompt injection, model drift) to non-technical audiences to drive security awareness and culture across the broader organization.

• Proven experience in offensive security, including AI Red Teaming/Penetration Testing against agentic frameworks and LLM integrations.
• Demonstrated ability to engineer or deploy AI Detection and Response (AIDR) workflows utilizing agentic and SIEM technologies, with a strong focus on AI-native threat modeling (e.g., MAESTRO framework).
• Understanding of Governance, Risk, and Compliance (GRC), specifically managing AI governance policies and enforcing the principle of least privilege for human and AI identities.
• Upper-Intermediate English fluency to ensure world-class communication.
• Strong presentation skills with the ability to translate technical security data for non-technical stakeholders.
• Ability to work in time zone alignment (EST/PST) to seamlessly integrate with cross-functional teams for agile project execution and incident response.
• A self-directed, passionate thinker dedicated to continuous innovation and modernized security solutions.