AI Security Engineer - Foundation Models & Guardrails

Mastercard; Bray; On-site; EUR 120,000 - 180,000; Full time

Job summary

Mastercard is seeking a Lead AI Security Engineer to join a strategic AI engineering team focused on foundation model security and responsible-AI practices. You will translate governance guidance into concrete security implementations and own the technical ownership of turning advies into tested solutions.

This role requires hands-on security engineering for ML/AI, testing for vulnerabilities, building guardrails, access controls, and bias mitigation.

Qualifications

• Hands-on experience testing ML/AI models for security vulnerabilities.
• Implement guardrails, input validation and access controls.
• Experience with bias/fairness testing in ML models.
• Familiarity with embeddings, foundation models and related security risks.
• Strong software engineering fundamentals and production tooling.

Responsibilities

• Implement the technical recommendations produced by central security and AI governance review teams.
• Test models for security vulnerabilities directly and assess risks such as membership inference and model inversion.
• Build and maintain guardrails and mitigations identified through testing or governance review.
• Implement bias and fairness testing for models and use cases.
• Provide concrete, reproducible test results to governance teams.

Skills

Adversarial testing

ML security

Access controls

Audit logging

Cloud platforms

Documentation & communication

Tools

Databricks

Job description

Mastercard is seeking a Lead AI Security Engineer to join a strategic AI engineering team focused on foundation model security and responsible-AI practices. You will translate governance guidance into concrete security implementations and own the technical ownership of turning advies into tested solutions.

This role requires hands-on security engineering for ML/AI, testing for vulnerabilities, building guardrails, access controls, and bias mitigation.