AI Security Engineer

As an AI Security Engineer, your role sits at the intersection of artificial intelligence and cybersecurity. You will be responsible for identifying, analyzing, and mitigating risks associated with AI/ML systems deployed in production environments.

You will begin by understanding how AI models are built, trained, and deployed. From there, your job is to secure every stage of the pipeline — including data ingestion, model training, inference, and API exposure.

A major part of your role involves detecting vulnerabilities such as adversarial attacks, data poisoning, and model inversion attacks. You will simulate attacks against machine learning models to identify weaknesses and improve system robustness.

You will also design secure AI architectures, ensuring that sensitive data is protected and models are not easily exploited. This includes implementing access controls, encryption, and monitoring mechanisms.

Another responsibility is collaborating with AI engineers and DevOps teams to integrate security into the ML lifecycle (DevSecOps for AI). You will help enforce best practices for secure coding, model validation, and deployment.

You will also monitor production systems, analyze anomalies, and respond to security incidents involving AI systems.

Job Requirements

You must have a strong foundation in both machine learning and cybersecurity.

Experience with Python and ML frameworks like TensorFlow or PyTorch is required. You should understand how models are trained and deployed.

Knowledge of cybersecurity concepts such as encryption, authentication, and network security is essential.

You should be familiar with adversarial machine learning techniques and common attack vectors.

Experience with cloud platforms (Azure preferred) and containerization (Docker, Kubernetes) is important.

Understanding of MLOps pipelines and CI/CD is a plus.

Strong analytical thinking and problem-solving skills are required.