Security Engineer - AI/ML Focus

Job Description

We're partnered with an established tech company at the forefront of AI innovation, and they're looking to hire a Security Engineer with a strong focus on AI/ML systems. This is an opportunity to join a high-impact team working on the next generation of machine learning platforms-where security, trust, and resilience are core to the mission.

You'll play a critical role in securing the company's AI/ML infrastructure, helping to build out end-to-end safeguards across data pipelines, model training environments, and deployment systems. This is a hands-on engineering role for someone who understands both traditional security practices and the unique challenges posed by modern AI/ML stacks.

Key responsibilities include:

• Designing and implementing security controls tailored to AI/ML workflows
• Identifying and mitigating ML-specific risks (e.g., model theft, adversarial inputs, data poisoning)
• Working closely with engineering and data science teams to embed security into model lifecycles
• Developing tooling and automation for secure deployment and continuous monitoring
• Staying current on the evolving threat landscape in AI and contributing to internal knowledge sharing

About you:

• 5+ years of experience in security engineering, ideally with exposure to ML systems
• Strong knowledge of threat modeling, secure coding, and cloud infrastructure security (AWS/GCP/Azure)
• Familiarity with ML frameworks (e.g., PyTorch, TensorFlow) and data platforms (e.g., Spark, Airflow)
• Proficiency in scripting or software development (Python preferred)
• Bonus: Experience in areas like LLM security, model interpretability, or data governance