AI Security Engineer

Huxley; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

Huxley seeks an AI Security Engineer to secure AI platforms and pipelines, focusing on risk assessment, threat modelling, and continuous monitoring of AI systems.

You will design security controls for AI/LLM, lead red/blue team exercises, test for prompt injection, and help secure CI/CD, APIs, and orchestration layers across distributed cloud environments. The role is based in Greater London with potential hybrid work.

Qualifications

• Strong background in security engineering and cloud security.
• Hands-on AI red teaming and adversarial testing experience.
• Familiarity with AI security tooling and LLM testing frameworks.
• Experience securing APIs and distributed systems.

Responsibilities

• Design and implement security controls for AI and LLM systems
• Perform AI-specific threat modelling and risk analysis
• Lead red team and blue team testing of AI platforms
• Conduct prompt injection and adversarial testing
• Implement monitoring, logging, and alerting for AI behaviour
• Secure AI pipelines, APIs, and orchestration layers
• Support secure deployment and CI/CD practices

Skills

Security engineering

Cloud security

AI red teaming

Adversarial testing

APIs / distributed systems security

Tools

LLM testing frameworks

AI security tooling

Job description

The AI Security Engineer is responsible for securing AI platforms and systems against adversarial threats.

The role focuses on technical security controls, threat modelling, red teaming, and continuous monitoring of AI systems.

Responsibilities:

• Design and implement security controls for AI and LLM systems
• Perform AI-specific threat modelling and risk analysis
• Lead red team and blue team testing of AI platforms
• Conduct prompt injection and adversarial testing
• Implement monitoring, logging, and alerting for AI behaviour
• Secure AI pipelines, APIs, and orchestration layers
• Support secure deployment and CI/CD practices

Skills & Experience:

• Strong background in security engineering and cloud security
• Hands-on experience with AI red teaming and adversarial testing
• Familiarity with AI security tooling and LLM testing frameworks
• Experience securing APIs and distributed systems