AI & Offensive Security Engineer - F/M/X

Join our team and start a new adventure in an international and dynamic environment, where you will be able to fulfill your career expectations in a fast-growing organization. Positioned at the heart of our evolution, our Data and AI team is pivotal in driving both team and organizational growth. As an AI & Offensive Security Engineer, you will play a critical role in ensuring the security, trustworthiness, and compliance of Mantu’s AI solutions by proactively identifying and mitigating risks associated with AI deployments and business processes. Your work will combine offensive security, penetration testing, red team exercises, and security testing of AI systems.

Your Missions:

• Plan and execute red team exercises to identify weaknesses in Mantu’s systems, processes, and security controls. 
• Perform adversarial testing of internal AI solutions, copilots, agents, and knowledge management platforms. 
• Assess risks related to data access, permissions, authentication, information exposure, and AI-generated actions. 
• Investigate how AI systems interact with enterprise data sources such as SharePoint, Teams, OneDrive, and business applications. 
• Identify attack paths that could lead to unauthorized access, data exposure, privilege escalation, or unintended actions. 
• Document findings clearly, provide practical remediation advice, and work with technical teams to fix identified issues. 
• Contribute to penetration testing methods, red team playbooks, and AI security testing practices. 
• Follow new attack techniques, vulnerabilities, AI threats, and developments in offensive security. 
• Conduct penetration tests on web applications, APIs, cloud environments, infrastructure, and business applications. 

Your Profile:

• Bachelor’s or Master’s degree in engineering, cybersecurity, computer science, or a related field. 
• 3 to 5 years of professional experience in cybersecurity, with a focus on offensive security, penetration testing, vulnerability assessment, or security research. 
• Hands-on experience with penetration testing methodologies, tools, and reporting. 
• Experience testing web applications, APIs, infrastructure, cloud environments, or enterprise applications. 
• Good understanding of common vulnerabilities, attack techniques, identity management, access control, and security assessment methods. 
• Experience taking part in, or conducting, red team exercises is a strong advantage. 
• A strong interest in AI tools, AI agents, and Large Language Models, with basic practical experience using or testing them. 
• Interest in AI security, adversarial testing, prompt injection, data exposure, and risks linked to AI-enabled applications. 
• An analytical and investigative mindset, with the curiosity to explore realistic attack scenarios. 
• Clear communication skills, with the ability to explain technical findings and business risks to different audiences. 
• A collaborative approach and the ability to work effectively with technical and business teams. 

 What we offer:

• An international community bringing together 110+ different nationalities
• An environment where trust has a central place: 70% of our key leaders started their careers at the first level of responsibilities
• A robust training system with our internal Academy and 250+ available modules
• A vibrant workplace that frequently gathers for internal events (afterworks, team buildings, etc.)
• At Mantu, sustainability is part of everything we do. You’ll have the opportunity to turn your ideas into action and make a tangible impact. Every day, our teams bring our ESG commitments to life, from reducing our footprint to driving positive change within our communities. Through our WeCare Together program, you’ll be empowered to design and lead projects that create real social or environmental impact, with the company’s full support.

Mantu is proud to be an equal-opportunity workplace. We are committed to promoting diversity within the workforce and creating an inclusive working environment. For this purpose, we welcome applications from all qualified candidates regardless of gender, sexual orientation, race, ethnicity, beliefs, age, marital status, disability, or other characteristics.