Principal AI Security Engineer—Foundation Models

VulnU; Dublin; Hybrid; EUR 120,000 - 180,000; Full time

Job summary

Mastercard is seeking a Lead AI Security Engineer to implement and test security controls for foundation models and AI use cases. You will translate central security and AI governance guidance into concrete, tested engineering work and ensure protections such as access controls, guardrails, and bias mitigations are part of production systems.

The role collaborates with security, privacy, and governance teams to stay ahead of emerging threats while delivering secure, compliant AI platforms across

Qualifications

• Hands-on experience testing ML/AI models for security vulnerabilities.
• Experience performing adversarial robustness testing and red-teaming of models.
• Strong applied security engineering skills to build real controls (guardrails, filters, access restrictions).
• Experience implementing bias/fairness testing/mitigation for ML models.
• Familiarity with security risks of embeddings and foundation models; knowledge of current research/attack techniques.
• Experience with access control and audit logging in distributed/hybrid environments.
• Knowledge of PCI DSS or data protection regulations for financial data.

Responsibilities

• Implement technical recommendations from security/governance teams into concrete engineering work.
• Test models for vulnerabilities and run practical risk assessments.
• Build and maintain guardrails, mitigations, and access controls.
• Conduct bias and fairness testing for models and use cases.
• Document test results, logs and benchmarks to support governance reviews.

Skills

ML security testing

Adversarial robustness

Security engineering

Access control

Data privacy & governance

Bias/fairness testing

Cloud security

Communication

Regulatory context

Education

Bachelor's degree in CS/Engineering

Tools

AWS

Databricks

API security tooling

Job description

Mastercard is seeking a Lead AI Security Engineer to implement and test security controls for foundation models and AI use cases. You will translate central security and AI governance guidance into concrete, tested engineering work and ensure protections such as access controls, guardrails, and bias mitigations are part of production systems.

The role collaborates with security, privacy, and governance teams to stay ahead of emerging threats while delivering secure, compliant AI platforms across