Engineer, AI Security Posture & Model Validation

About the role

The GCS – Security Architecture function secures Carnival Corp’s adoption of AI by ensuring GenAI, model, and agentic systems are deployed, validated, and operated against published security standards. This position is a hands-on engineering role focused on AI security posture, model validation, and securing the inference layer.

Essential Functions

• Implement and operate AI security posture management (AISPM/DSPM) across model and inference infrastructure; identify misconfigurations, drift, and risk in AI workloads and drive remediation.
• Design, build, and run model validation and evaluation harnesses to test AI models and pipelines for robustness, data leakage, and unexpected behavior before and after deployment.
• Build and maintain inference-layer guardrails and controls (input/output filtering, rate and access controls) for GenAI and agentic applications.
• Define and enforce PHI/PII and data-protection controls, and identity/access controls (least-privilege, agent-to-agent authentication) for AI systems.
• Partner with Cloud Security to establish and validate guardrails in AWS and Azure for AI workloads.
• Develop scripts, automation, and tooling (primarily Python) to integrate AI security controls and automated testing into CI/CD pipelines and engineering workflows.
• Document secure architecture patterns, anti-patterns, and reference materials for model deployment and inference, and provide remediation guidance to engineering teams.
• Research, test, and pilot AI security tools and utilities aligned to the NIST AI RMF and related standards.
• Transition matured AI security monitoring to security operations teams.

Knowledge, Skills & Abilities

• Strong scripting and automation skills (especially Python) for security tooling, evaluation harnesses, and automated testing of AI systems.
• Hands-on experience validating AI/ML models and securing the inference layer.
• Working knowledge of Identity and Access Management and data security/privacy controls (PHI/PII, encryption).
• Applied understanding of the NIST AI RMF and related AI security frameworks.
• Ability to communicate AI security concepts in non-technical terms to business stakeholders.

Essential/Minimum qualifications

• Bachelor's degree in Cyber Security, Computer Science, Artificial Intelligence, or a related field (Master's a plus).
• Cloud environment (Azure & AWS) security fundamentals.
• Strong programming/scripting ability (Python).
• Knowledge of machine learning concepts, secure MCP configuration, Application/API security, and data protection.

Essential Experience Required

• 3+ years (mid-level) in Cyber Security, AI/ML, or security engineering in a large enterprise setting.
• Identity and Access Management fundamentals.
• Hands-on experience with model validation, security tooling and automation, and applying the NIST AI RMF to AI workloads.

Work Conditions

• Work primarily in a climate-controlled environment with minimal safety/health hazard potential.