AI Security Engineer: Guard AI Lifecycle & LLMs

Netrolynx AI; United Kingdom; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Health insurance

Retirement plans

Paid time off

Training programs & certifications

Flexible working arrangements

Diversity & inclusion

Job summary

Vbeyond in the United Kingdom is seeking an experienced AI Security Engineer to secure AI, ML, and Generative AI solutions across enterprise environments. You will embed security controls throughout the AI lifecycle and safeguard LLMs, foundation models, and data pipelines.

You will work closely with data scientists, AI engineers, and governance teams to enable secure development, deployment, and operation of AI solutions, applying threat modeling, red teaming, and secure CI/CD practices.

Qualifications

• Minimum 8 years of relevant professional experience in AI security engineering.
• Strong understanding of AI/ML lifecycle security risks including LLMs and Generative AI.
• Hands-on experience with AI red teaming, threat modeling, vulnerability assessment, and security testing.

Responsibilities

• Perform comprehensive security assessments and threat modeling for AI/ML/Generative AI solutions.
• Design, implement, and monitor AI security controls and safeguards across the lifecycle.
• Conduct AI red-team exercises to test defenses against prompt injection and adversarial threats.
• Secure model development, training, evaluation, deployment, and operations with secure practices.
• Integrate security controls within AI CI/CD pipelines and configuration management.

Skills

AI Security

Threat Modeling

Red Teaming

DevSecOps

Cloud Security

Communication

Tools

CI/CD Pipelines

Vulnerability Scanners

Security Audits

Job description

Vbeyond in the United Kingdom is seeking an experienced AI Security Engineer to secure AI, ML, and Generative AI solutions across enterprise environments. You will embed security controls throughout the AI lifecycle and safeguard LLMs, foundation models, and data pipelines.

You will work closely with data scientists, AI engineers, and governance teams to enable secure development, deployment, and operation of AI solutions, applying threat modeling, red teaming, and secure CI/CD practices.