GenAI Security Specialist

ActiveFence Ltd; United Kingdom; On-site; GBP 70,000 - 95,000; Full time

Job summary

A leading security solutions provider in the UK seeks a Red Team Specialist to analyze and test the security of generative AI models. You will assess vulnerabilities and collaborate with teams to enhance model resilience. Ideal candidates have over 5 years of offensive cybersecurity experience and strong analytical skills. Join us to safeguard cutting-edge technologies and make a global impact.

Qualifications

• 5+ years of experience in offensive cybersecurity focused on cloud and API security.
• Strong understanding of AI technologies and generative models.
• Exceptional analytical and problem-solving skills.

Responsibilities

• Execute comprehensive attacks on generative foundational models.
• Collaborate with security teams to implement risk mitigation strategies.
• Document all red team activities and findings.

Skills

AI vulnerability analysis

Cloud security

API security

Python

Analytical skills

Communication skills

Education

Bachelor’s or Master’s degree in Computer Science

Tools

Machine learning development frameworks

Job description

Overview

What We Are Looking For

As a Red Team Specialist focused on GenAI models, you will play a critical role in safeguarding the security and integrity of commercial cutting-edge AI technologies. Your primary responsibility will be to analyze and test commercial GenAI systems including, but not limited to, language models, image generation models, and related infrastructure. The objective is to identify vulnerabilities, assess risks, and deliver actionable insights that strengthen AI models and guardrails against potential threats.

Responsibilities

• Execute sophisticated and comprehensive attacks on generative foundational models and agentic frameworks.
• Assess the security posture of AI models and infrastructure, identifying weaknesses and potential threats.
• Collaborate with security teams to design and implement effective risk mitigation strategies that enhance model resilience.
• Apply innovative testing methodologies to ensure state-of-the-art security practices.
• Document all red team activities, findings, and recommendations with precision and clarity.

Requirements

Must-Have

• Proven track record in AI vulnerability analysis.
• Strong understanding of AI technologies and underlying architectures, especially generative models and frameworks.
• Minimum of 5 years of experience in offensive cybersecurity, with a focus on cloud and API security.
• Familiarity with agentic frameworks and hands-on experience in agentic development.
• Proficiency in Python.
• Exceptional analytical, problem-solving, and communication skills.
• Ability to thrive in a fast-paced, dynamic environment.

Nice-to-Have

• Bachelor’s or Master’s degree in Computer Science, Information Security, or a related field.
• Demonstrated experience building production-quality pipelines and automations.
• Hands-on experience with machine learning development frameworks and environments.
• Advanced certifications in offensive cybersecurity (e.g., OSWE, OSCE3, SEC542, SEC522).
• Certifications or background in DevOps/ML domains.
• Webint / OSINT experience.

About ActiveFence

ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the world’s largest enterprises and tech platforms every day.

As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.