GeorgiaTEK Systems Inc. · 1 day ago
AI Penetration Tester - Remote
GeorgiaTEK Systems Inc. is seeking an AI Penetration Tester to execute AI-focused penetration testing engagements. The role involves manual testing of AI/ML systems, threat modeling, and collaboration with security teams to enhance organizational security by identifying and mitigating risks across AI-powered systems.
Responsibilities
Execute AI-focused penetration testing engagements across AI/ML systems, web applications, APIs, and mobile clients
Perform threat modeling for AI-powered software systems and evaluate AI-related business logic
Conduct architecture reviews with a focus on adversarial ML vectors, prompt-based vulnerabilities, and AI-specific security risks
Develop and enhance AI-driven tools and methodologies for offensive security tasks such as discovery, exploitation, fuzzing, and adversarial ML testing
Demonstrate penetration testing findings to technical and non-technical audiences, including live demos
Collaborate with engineering, development, and security teams to communicate findings, guide remediation, and advise on secure AI model development and deployment
Research emerging AI attack techniques, assess potential impact, and provide actionable recommendations to strengthen AI defenses
Partner with internal Red Teams, SOC analysts, and AI security researchers to share insights and refine AI red teaming methodologies
Lead AI penetration testing engagements independently from planning through execution and reporting with minimal oversight
Qualification
Required
Minimum 3+ years of recent penetration testing experience focused on APIs, web applications, and mobile applications
Strong communication and presentation skills for both technical and non-technical stakeholders
Bachelor's degree from an accredited university or equivalent industry experience
Preferred
Experience in AI model testing or AI security is highly desirable
Proven background in AI red teaming and adversarial attack development, including: Prompt engineering attacks, LLM-based vulnerability analysis, Model evasion techniques
Proficiency with penetration testing tools: Burp Suite Pro, Netsparker, Checkmarx
Experience with AI security frameworks and tools: TensorFlow, PyTorch, LLM APIs, LangChain
One or more ethical hacking certifications such as: GWAPT, CREST, OSWE, OSWA