AI security consultant

📢 Job Opening: AI Security Consultant at Cyberlabs IsraelJoin the forefront of AI Security, Governance, and Risk Management!

Cyberlabs Israel is a leader in providing Real-World Security for AI, Cloud & Blockchain. As AI adoption accelerates and integrates into the core of business processes , organizations face unique and new attack vectors. We are looking for a highly skilled and motivated AI Security Consultant to help our enterprise clients secure their next-generation AI systems.

As an AI Security Consultant, you will be a key member of our team, responsible for assessing, hardening, and governing our clients' critical AI assets. You will work on the cutting edge of cybersecurity, bridging the gap between traditional IT security and the unique demands of Machine Learning (ML).

• Risk Assessment & Penetration Testing: Conduct comprehensive AI risk assessments, including simulating adversarial attacks on AI models (e.g., Prompt Injection, Data Poisoning, and Model Extraction/Theft).
• Model & Data Hardening: Design and implement technical controls for Model Hardening, such as input filters against Prompt Injection and API Rate Limiting for Model Theft prevention.
• MLSecOps Implementation: Integrate security tools and processes into the ML CI/CD pipelines to secure the ML supply chain.
• AI Governance & Compliance: Guide clients in establishing AI Governance frameworks, ensuring compliance with global regulations like the EU AI Act and adherence to standards like NIST AI RMF and ISO/IEC 42001.
• Bias and Explainability: Advise on identifying and mitigating model bias and implementing eXplainable AI (XAI) tools to meet regulatory and management transparency demands.

• Proven experience in Cybersecurity, with specific experience or deep knowledge in AI/ML security (AI/ML models and the ML lifecycle).
• Familiarity with adversarial attacks against AI models (e.g., Prompt Injection, Data Poisoning).
• Knowledge of AI governance frameworks and global regulations (e.g., EU AI Act, NIST AI RMF).
• Experience with Cloud security environments (AWS, Azure, GCP).
• Strong analytical, communication, and client-facing skills.

• Integrated Expertise: You will work with experts who deeply understand AI, Cloud, and Blockchain.
• Offensive Approach: We maintain an attacker's mindset to identify critical weaknesses.
• Full-Spectrum Solution: Be part of a team that provides end-to-end service, from Risk Assessment to technical and regulatory control implementation.

Ready to become an Orchestrator of AI Security?

If you are passionate about pioneering AI security and ready for the CISO's new challenge