Cybersecurity DevOps Engineer

Cybersecurity DevOps Engineer

Glasgow

JR022711

Morgan Stanley are seeking an AI DevOps Engineer, to join our Testing Execution team in Security Testing and Risk, to perform adversarial testing to evaluate the efficacy of the model-level security controls and the controls implemented between the end-user and the LLM.

Cyber Data Risk & Resilience:

The mission of Cyber Data Risk & Resilience (CDRR) is to deliver first-line defenses to manage risks to Firm technology, information and cyber threats through risk identification, control management and assurance. This allows the business to operate and grow in a secure and legally compliant manner. Our vision is to deliver Programs that protect and enable the business, ensure secure delivery of services to our clients, adjust to address the risks presented by an evolving threat landscape, meet regulatory expectations, and offer highly attractive career opportunities.

• Communicate regularly with product leads across the technology organization and discuss opportunities for improvement to existing and future technology solutions.
• Operate a security testing platform designed to perform adversarial testing against AI/LLM systems.
• Detect and validate risks in AI/LLM systems including but not limited to evasion, prompt injection, and data leakage.
• Collaborate with AI/ML engineers and Gen AI application developers to integrate domain-specific security knowledge into AI/LLM systems.
• Deploy and manage cloud resources and infrastructure components.

• 4+ years experience in cybersecurity technologies or operations, including areas such as red teaming, penetration testing, application security, vulnerability management, compliance, and governance.
• Strong programming and scripting skills (e.g., Python, Java, C, C++, Bash)
• Basic Linux and Windows command-line knowledge
• Knowledge of cloud security best practices and compliance standards
• Familiarity with LLMs and techniques like prompt engineering, fine-tuning, and retrieval-augmented generation (RAG).
• Advanced understanding of business line and discipline with some knowledge of competitive environment and other disciplines.
• Good understanding of the tactics, techniques and procedures of threat actors.
• Knowledge of the MITRE ATLAS Framework and the OWASP Top 10 for LLM Applications.
• Background in AI threat modeling, attack mitigation, or misuse detection.
• Proficiency in cloud platforms such as AWS, Azure, and Google Cloud
• Understanding of containerization and orchestration using Docker and Kubernetes
• Understanding of data analysis
• Excellent problem-solving
• Excellent attention to detail and communication
• Excellent stakeholder management