ML Model Security & Privacy Architect (m/f/d)

Join our Innovation Team, where we explore cutting-edge concepts at the intersection of Machine Learning and Security. Our mission is to develop forward-looking solutions—such as model protection, privacy-preserving ML, security for agentic AI, and anomaly detection—that will later be integrated into our Edge products. This requires high-level innovation skills combined with a hands-on mindset.

About

If you are passionate about building secure AI systems, exploring new ideas, and turning concepts into prototypes, this role is for you:

Define strategies and implement solutions for protecting ML models and sensitive data during deployment. Focus areas include IP protection, privacy-preserving inference, and resilience against adversarial manipulation.

Responsibilities

• Design and implement model obfuscation and secure packaging techniques.
• Develop IP protection strategies.
• Enable secure execution environments for customer models using TEEs.
• Assess and mitigate adversarial ML threats (evasion, poisoning attacks).
• Define privacy-preserving inference mechanisms (e.g., differential privacy).

Advise on compliance with AI security and privacy regulations (GDPR, EU AI Act).

Required Skills

• Have a background in Computer Science, Cybersecurity, or Cryptography and a strong interest in applied ML, OR
• Have a background in Machine Learning and an interest in cybersecurity.
• Knowledge of model protection techniques and IP security.
• Familiarity with adversarial ML attacks and defenses.
• Understanding of TEEs and secure enclaves.
• Knowledge of privacy-preserving ML concepts (differential privacy, federated learning basics).
• Awareness of regulatory frameworks for AI security and privacy.
  
  

Please note: The successful candidate may/will be responsible for security related tasks. The assignment may/will be in scope of security certifications, therefore a conscious and reliable way of working is necessary.

More information about NXP in Austria...