AI Platform Delivery Manager

Key Responsibilities :

Execute AI-focused penetration testing engagements that include manual testing of systems with AI / ML integration.

Perform threat modeling for AI-powered systems, evaluate AI-related business logic, and conduct architecture reviews.

Develop and enhance AI-driven tools and methodologies for offensive security tasks.

Demonstrate AI penetration testing findings to both technical and non-technical audiences.

Research emerging AI attack techniques, vulnerabilities, and provide actionable recommendations.

Collaborate with internal teams to communicate findings, lead discussions, and advise on secure AI model development.

Required Qualifications :

Minimum 3 years of recent penetration testing experience focused on APIs, web apps, and mobile apps.

Proven background in AI red teaming and adversarial attack development.

Proficiency with penetration testing tools and AI security frameworks.

Strong communication and presentation skills.

One or more major ethical hacking certifications.

Bachelor s degree in a relevant field or equivalent experience.

Technical Skills & Experience :

Experience with AI model testing or AI security highly desirable.

Knowledge of prompt engineering attacks, LLM-based vulnerability analysis, and model evasion techniques.

Proficiency in tools like Burp Suite Pro, Netsparker, Checkmarx, and AI security frameworks.

Certifications or training in AI security techniques.

Preferred Qualifications :

Experience with AI & Generative AI.

Specialization in Penetration Testing.