AI Cyber​/Risk Consultant

AI Security Reviewer

Serve as an early-stage AI security reviewer for new AI initiatives entering the organization. Review AI use cases, architecture diagrams, integrations, and data flows to identify security risks. Develop and execute AI security testing methodologies and validation procedures. Perform adversarial testing against AI models, copilots, assistants, and agentic AI workflows. Conduct prompt injection, jailbreak, policy bypass, and sensitive data exposure testing.

Evaluate AI guardrails and recommend improvements to security controls. Assess risks associated with AI inputs, outputs, retrieved context, embeddings, and generated responses. Partner with engineering, platform, architecture, governance, and privacy teams to secure AI deployments. Define AI security requirements and control expectations for enterprise AI solutions. Translate traditional DLP and data protection policies into AI-specific control frameworks. Implement and recommend safeguards to prevent sensitive data leakage through AI systems.

Assess AI data retention, minimization, and privacy risks. Support DSPM initiatives and improve visibility into sensitive data exposure through AI capabilities. Establish monitoring strategies for AI abuse patterns, anomalous activity, suspicious prompts, and data exfiltration indicators. Document risk assessments, security recommendations, mitigation plans, and executive-facing reports. Support governance activities aligned to AI risk management and lifecycle frameworks. Collaborate closely with Mike DeZenzo's team, Chad Mauer's engineering organization, and broader AI security stakeholders to protect emerging AI platforms and enterprise AI initiatives.