TL;DR
Senior Embedded AI Platform Security Engineer (AI Security): Developing forward-looking security solutions for Machine Learning and integrating them into Edge products with an accent on model protection, privacy-preserving ML, and anomaly detection. Focus on building security tools for ML artifacts, designing secure APIs for embedded platforms, and performing threat modeling for ML systems.
Location: Onsite in Glasgow (UK), Gratkorn (Austria), or Leuven (Belgium).
Company
hirify.global N.V. is a world leader in secure connectivity solutions for embedded applications, innovating for a smarter, safer, and more sustainable world.
What you will do
- Build security scanning tools for ML artifacts and deployment workflows.
- Design secure APIs for model integration on embedded platforms.
- Perform threat modeling for ML systems, including poisoning, evasion, and prompt injection.
- Implement monitoring solutions for model integrity and anomaly detection.
- Ensure compliance with NIST AI Risk Management Framework and similar standards.
- Collaborate with internal teams to integrate security checks into development pipelines.
Requirements
- Background in Computer Science, Cybersecurity, Cryptography, or Machine Learning with an interest in the respective complementary field.
- Strong Python development for automation and tooling.
- Experience with threat modeling methodologies adapted for ML systems.
- Knowledge of adversarial ML attacks and defenses.
- Familiarity with secure API design and integration.
- Understanding of compliance frameworks (NIST AI RMF, ISO/IEC AI security standards).
Culture & Benefits
- Opportunities for career development with online and offline learning.
- Commitment to sustainability and measurable year-on-year progress.
- Inclusive work environment with programs for diversity, inclusion, and equality.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →