Senior AI Security Penetration Tester

Bureau Veritas Cybersecurity is seeking a Senior AI Security Penetration Tester to join their team in Amsterdam, North Holland, Netherlands. This role offers the opportunity to work at the forefront of AI and cybersecurity, helping organizations secure their AI solutions.

Bureau Veritas Cybersecurity is an expert partner in cybersecurity, assisting organizations with risk identification, defense strengthening, and compliance. They cover people, processes, and technology, operating across IT, OT, and IoT environments with over 300 cybersecurity professionals globally. They are part of the Bureau Veritas Group, a world leader in testing, inspection, and certification.

If you are passionate about offensive security and the evolving landscape of AI, join Bureau Veritas Cybersecurity and grow with the latest AI developments.

Company Overview

Bureau Veritas Cybersecurity is your expert partner in cybersecurity. We help organizations identify risks, strengthen defenses and comply with cybersecurity standards and regulations. Our services cover people, processes and technology, ranging from awareness training and social engineering to security advice, compliance and penetration testing. We operate across IT, OT and IoT environments, supporting both digital systems and connected products. With over 300 cybersecurity professionals worldwide, we combine deep technical expertise with a global presence. Bureau Veritas Cybersecurity is part of the Bureau Veritas Group, a global leader in testing, inspection and certification.

Quick Details

• Job Type: Full-time
• Experience: Mid-Senior level

Key Responsibilities

• Perform security assessments and penetration tests on AI applications, chatbots, and generative AI platforms.
• Test Large Language Models (LLMs) and AI integrations for vulnerabilities like prompt injection, jailbreaks, data leakage, and model manipulation.
• Identify and exploit weaknesses in AI/ML pipelines, AI agents, and autonomous workflows.
• Conduct web application, CI/CD, API, and cloud security assessments.
• Simulate realistic attack scenarios, from reconnaissance to post-exploitation.
• Analyze AI-specific risks such as prompt injection, data and model poisoning, and unbounded consumption.
• Develop new attack techniques, tooling, and testing methodologies for AI systems.
• Contribute to AI Security Research & Development and thought leadership.
• Guide and coach less experienced consultants in the field.

Requirements

• Minimum several years of experience in web application security, API security, and penetration testing.
• Affinity with artificial intelligence, machine learning, and generative AI.
• Knowledge of OWASP Top 10 for LLM Applications and AI-specific attack techniques.
• Familiarity with modern web applications, cloud platforms, and API architectures.
• Experience with Python, API testing, security automation, or security tooling.
• Ability to think like an attacker: creative, curious, critical, and persistent.
• Strong communication skills to convey complex findings to clients.
• Certifications such as CWES, OSCP, OSEP, OSWE, AI300, HTB COAE.
• Experience with LLM red teaming, prompt engineering, and adversarial machine learning.
• Experience with secure software development and DevSecOps.
• Proficiency in Dutch and English.

Benefits

• Work on challenging assignments in a team of experts who share your passion for cybersecurity.
• Share knowledge, conduct research, and challenge each other technically.
• Investment in training, certifications, conferences, and research.
• Work in an environment with a demonstrably high level of expertise.
• Engage in projects of national importance.
• Contribute to the development of standards and share knowledge within the cybersecurity community.
• Receive the CCV-keurmerk Pentesten.
• Work in a safe, inclusive, and positive work environment.
• Support for well-being and team bonding through team activities and access to OpenUp.com.
• Stimulate a healthy work-life balance with flexible working options.