You will primarily be responsible for: ​ 

• Lead adversarial security reviews of AI-enabled systems, gateways, APIs, and automation platforms to validate architectural and operational resilience

• Contribute to security and architecture reviews to ensure AI and core security components are designed and operated securely from MVP through target state

• Design, assess, and challenge security architectures for AI agents, automation workflows, identity flows, and trust boundaries

• Develop and maintain automated Red Team tooling to continuously test exposed attack surfaces and security assumptions

• Translate Red Team findings into architectural guidance, security patterns, and actionable design improvements

• Produce clear security architecture and threat documentation for AI and automation technologies

• Work closely with engineering, platform, and operations teams to validate security controls and operational readiness

• Provide expert support during security incidents, design escalations, and high-risk technical decisions

Your profile:​ 

• Strong background in offensive security and Red Team operations

• Proven experience in security architecture and secure system design

• Hands-on automation and scripting experience (Python required)

• Solid understanding of APIs, distributed systems, identity, and authorization models

• Practical experience assessing AI systems, agents, or automation frameworks

• Confident, pragmatic, and comfortable challenging design decisions

• Self-starter with the ability to operate autonomously in ambiguous environments

• Clear and effective written and verbal communication skills

• Able to adapt quickly to changing priorities while managing multiple initiatives

• Comfortable working independently or as part of cross-functional teams

• Experience in regulated or financial environments is a strong plus

• Certified knowledge of Cloud Environments such as Azure and AWS is also a plus

Apply by submitting a CV in English.