TL;DR
Embedded AI Platform Security Engineer (AI): Developing cutting-edge security solutions for Machine Learning models and systems to be integrated into Edge products with an accent on model protection, privacy-preserving ML, and anomaly detection. Focus on building security scanning tools, designing secure APIs for embedded platforms, and performing threat modeling for ML pipelines.
Location: Hybrid in Gratkorn, Austria; Glasgow, UK; or Leuven, Belgium. Home office and flexible working time available.
Company
hirify.global is a corporation focused on exploring cutting-edge concepts at the intersection of Machine Learning and Security for integration into Edge products.
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 (poisoning, evasion, 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 strong interest in the other domain.
- 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).
- Conscious and reliable way of working is necessary due to security-related tasks and certifications.
Culture & Benefits
- Market competitive compensation.
- Home office and flexible working time.
- Meal benefits.
- Join an Innovation Team exploring cutting-edge concepts.
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 →