AI Security Engineer — Secure AI Lifecycle & Red Teaming

Netrolynx AI; United Kingdom; Presencial; GBP 110.000 - 140.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health Insurance

Paid Time Off

Learning Opportunities

Flexible Work

Descripción de la vacante

Vbeyond 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 strengthen safeguards for LLMs, foundation models, data pipelines, and AI-enabled applications.

The role requires hands-on AI red teaming and collaboration with data scientists, AI engineers and governance teams to define and enforce security standards, ensure compliant deployments, and continuously

Formación

• Minimum 8+ years of relevant experience in AI security engineering or related fields.
• Strong background in securing AI/ML lifecycle stages, including model development, training, evaluation, deployment and operations.
• Hands-on experience with AI red teaming, vulnerability assessments, threat modeling and security testing techniques.
• Familiarity with secure CI/CD pipelines, configuration management, and cloud security.
• Certifications such as CISSP, CCSP, CISM or equivalent; cloud security certifications from AWS/Azure/Google Cloud are desirable.
• Excellent problem-solving, analytical, communication and stakeholder management skills.

Responsabilidades

• Perform comprehensive security assessments and threat modeling for AI/ML/LLM-based solutions to identify vulnerabilities and mitigate risks.
• Design, implement, and monitor AI security controls, guardrails and detection capabilities to prevent and respond to incidents.
• Conduct AI red-team exercises simulating prompt injection, jailbreaks, model manipulation, data leakage and adversarial attacks.
• Secure the entire AI lifecycle including development, training, evaluation, deployment and ongoing operations.
• Embed security controls within AI CI/CD pipelines and configuration management processes.
• Collaborate with data scientists, AI engineers, architects and governance teams to define AI security standards.
• Analyze emerging AI threats to continuously improve defensive controls and testing methodologies.
• Provide guidance, training and best practices for secure and responsible AI adoption.

Conocimientos

AI security

Threat modeling

Red teaming

CI/CD security

Cloud security

Communication

Educación

CISSP

CCSP

CISM

Herramientas

AWS

Azure

Google Cloud

Descripción del empleo

Vbeyond 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 strengthen safeguards for LLMs, foundation models, data pipelines, and AI-enabled applications.

The role requires hands-on AI red teaming and collaboration with data scientists, AI engineers and governance teams to define and enforce security standards, ensure compliant deployments, and continuously