AI/ML Security Engineer

AI/ML Security Engineer

SWIFT

Brussels or Leiden

What to expect:

• Design, develop, and implement security frameworks and strategies to protect AI/ML models and their use, and related data, applications and systems from adversarial attacks and other security threats;
• Develop standards and best practices for a secure use, development, deployment, and operationalization of AI/ML (predictive AI, generative AI and Large Language Models);
• Analyze potential security risks in AI/ML applications, such as model poisoning, data leakage, and other adversarial machine learning threats, and define mitigations that can be effectively implemented;
• Collaborate with cross-functional teams to ensure AI/ML systems are integrated, deployed or leveraged with robust security practices throughout the development lifecycle of proprietary models, or through the implementation of pre-trained models, AI-based SaaS solutions, ...;
• Research and stay ahead of emerging security threats in AI/ML and propose innovative defense strategies;
• Conduct security assessments and robustness testing of AI/ML models, with appropriate tooling, identifying weaknesses and providing recommendations for improvement.
• Collaborate with internal teams to ensure compliance with relevant regulations, standards, and security frameworks in AI/ML-related initiatives;
• Provide guidance and act as centre of expertise for business, technical, legal, privacy and risk teams on assessing risks and implementing controls for AI/ML projects;
• Effectively communicate complex AI/ML security assessments, risks, controls and mitigations to management, technical teams and non-technical stakeholders.

What you need to be successful:

• University degree in Computer Science, AI/ML, Cybersecurity or related field, or equivalent experience;
• 8-10 years of relevant experience, including in AI/ML models development and deployment;
• Proficiency in programming languages such as Python, Java, or C++, and in AI/ML frameworks and libraries such as TensorFlow, PyTorch, scikit-learn, Keras, and XGBoost;
• Strong understanding of security concepts, including secure coding practices, threat modeling, and risk assessment;
• Expertise in securing AI/ML systems, including protection against adversarial attacks, data poisoning, ensuring the integrity of model training and inference processes, confidentiality of model and trained data;
• Strong analytical and problem-solving skills, attention to detail, and ability to work in a collaborative team environment;
• Excellent communication skills, including the ability to translate complex technical information for a non-technical audience.

Apply Now