AI Security Engineer

JOB Summary:

We are seeking a highly skilled AI Security Engineer to join our security team. This role is responsible for securing AI/ML systems, models, and data pipelines against emerging threats and adversarial attacks. The ideal candidate will have a strong foundation in cybersecurity principles combined with hands-on experience in AI/ML technologies and security best practices and attack vectors for those applications.

Role & responsibilities

AI/ML Security Design & Implementation

• Secure AI/ML models, APIs, and training pipelines against adversarial attacks, data poisoning, and model theft.
• Collaborate with AI HUB engineering teams to understand the current securityposture and integrate security-by-design principles into AI solutions.
• Design and implement KPIs to detect anomalies in AI behavior.
• Perform security tests and audits against current applications according to industry best practices (OWASP top 10 for LLM Applications etc.)

Threat Modeling & Risk Management

• Conduct threat modeling and risk assessments for AI/ML systems.
• Evaluate vulnerabilities in AI workflows, datasets, and deployed models.
• Define mitigation strategies for data integrity, model explainability, and bias-related risks.

Security Operations

• Monitor AI systems for adversarial activity and drift in production.
• Investigate incidents involving AI misuse, manipulation, or unintended behaviors.
• Leverage automated tools to continuously test AI models against known attack
• patterns.

Collaboration & Documentation

• Partner with AI HUB, data scientists, engineers, and product teams to ensure secure
• deployment of AI/ML solutions.
• Document best practices, policies, and playbooks for AI/ML security.
• Provide security training and awareness sessions tailored for AI/ML practitioners

Preferred candidate profile

• Proven experience in cybersecurity with exposure to AI/ML environments.

• Knowledge of AI/ML frameworks (TensorFlow, PyTorch, Scikit-learn) and deployment platforms (SageMaker, Vertex AI, Azure ML).

• Understanding of adversarial machine learning techniques, model inversion, and data poisoning attacks.

• Familiarity with cloud security (AWS, GCP, Azure) and API security practices.

• Proficiency in at least one programming language for automation and model testing.

• Strong analytical, research, and problem-solving skills.

GOOD TO HAVE

• Experience with AI governance, model interpretability, and fairness frameworks.

• Knowledge of privacy-enhancing technologies (federated learning, differential privacy, homomorphic encryption).