Sr. AI Application Security Pentester

AI is transforming how we deliver value—and securing these systems is critical. If you're passionate about breaking things to make them stronger and want to be at the forefront of AI security, this is your opportunity. We are seeking an experienced security professional to lead penetration testing and vulnerability assessments for AI-driven platforms, including chatbots, large language models (LLMs), and machine learning pipelines.

This role combines deep technical expertise in application security with emerging AI security practices to safeguard our AI systems and integrations.
This Hybrid role (in office Tues-Wed-Thurs) can be based in Charlotte, NC, Dallas, TX, or Malvern, PA

• Lead AI Security Assessments:
  Design and execute penetration tests targeting AI applications, LLM integrations, and machine learning workflows.
• Identify Vulnerabilities:
  Conduct adversarial testing, model robustness evaluations, and risk analyses to uncover weaknesses in AI architectures, training data, and deployment environments.
• Collaborate Across Teams:
  Work closely with engineering and data science teams to implement secure development practices and mitigate AI-specific risks.
• Develop Best Practices:
  Establish security standards for AI systems, update policies, and recommend enhancements to address emerging threats.
• Ensure Compliance:
  Validate adherence to ethical, regulatory, and industry standards for AI security.
• Stay Ahead of Trends:
  Act as a subject matter expert on AI security, monitoring evolving threats and technologies.
• Support Broader Security Initiatives:
  Participate in enterprise-wide security assessments, risk analyses, and contingency planning for critical systems.

• Experience:
  
  Minimum 8 years in IT security, application security, or penetration testing, with hands-on experience in AI/ML environments preferred.
• Education:
  
  Undergraduate degree in a related field or equivalent combination of training and experience.
• Certifications:
  
  Preferred credentials include CISSP, GPEN, GWAPT, CEH, or similar.

Strong knowledge of penetration testing methodologies and tools.

Familiarity with AI/ML frameworks, adversarial attack techniques, and model security.

Understanding of secure coding practices and cloud environments.