AI Cybersecurity Engineer – Offensive Security, Threat Modeling

This is a fully remote position, open to applicants in Serbia.

📋 Description

• Predictive AI Threat Modeling: Spearhead sophisticated threat-modeling initiatives across the bank’s localized AI/ML pipelines, data repositories, and training environments. Anticipate advanced attacker behaviors to establish preemptive security measures prior to model deployment in production.

• AI Red Teaming & Offensive Simulations: Execute targeted offensive maneuvers and ethical hacking against our on-premises AI infrastructure. Simulate genuine adversarial attacks, including data poisoning, model inversion, membership inference, evasion attacks, and prompt injection.

• Framework Mapping with MITRE ATLAS: Deploy and operationalize the MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) framework. Align identified vulnerabilities with ATLAS tactics and techniques to create a comprehensive, AI-focused defensive matrix that corresponds with traditional MITRE ATT&CK.

• On-Premises Infrastructure Hardening: Evaluate and secure the physical and virtual infrastructure that supports our AI workloads, including bare-metal GPU clusters, local containerized environments (Kubernetes/OpenShift), and private data registries, ensuring rigorous isolation from external threats.

• Proactive Risk Management & Early Detection: Partner with the SOC and data engineering teams to develop predictive detection use cases and custom alerts. Recognize early indicators of an AI-targeted attack or data exfiltration effort before malicious actors can undermine model integrity.

⛳️ Requirements

• Professional Experience: A minimum of 5 years of focused experience in Offensive Security, Red Teaming, or Advanced Penetration Testing, with a demonstrated ability to pivot and at least 2 years of practical experience securing or attacking AI/ML workloads.

• Banking Sector Experience (Mandatory): Prior engagement with a regulated financial institution in Egypt. An understanding of the security limitations, compliance requirements, and audit rigor mandated by the Central Bank of Egypt (CBE) for on-premises operations is essential.

• Deep Mastery of AI Attack Frameworks: Extensive knowledge of MITRE ATLAS and the OWASP Top 10 for Large Language Models (LLMs). A proven history of converting these theoretical frameworks into actionable, automated offensive playbooks is required.

• On-Prem & Core Technical Skills: Strong command of Python or bash scripting to create custom exploit or testing tools.

• In-depth understanding of on-premises infrastructure components (Linux administration, private networking, storage area networks).

• Direct experience with container security (Docker, Kubernetes) and secure MLOps pipelines.

• Education & Certifications: Bachelor’s degree in Computer Science, Cybersecurity, Computer Engineering, or a closely related field.

• Highly regarded offensive certifications: OSCP, OSCE, CRTP, or GPEN, along with any specialized AI/ML security qualifications.

• Mindset & Communication: A consistently inquisitive, adversarial mindset coupled with robust risk management practices. The capability to effectively communicate complex, highly technical AI vulnerabilities into actionable remediation strategies for data scientists and senior banking executives. Proficiency in English.

🏝️ Benefits

• Attractive, market-leading salary package

• Clear career advancement path with professional development opportunities