Senior Security Consultant (AI/ML Penetration Tester)

NetSPI® pioneered Penetration Testing as a Service (PTaaS) and leads the industry in modern pentesting. Combining world-class security professionals with AI and automation, NetSPI delivers clarity, speed, and scale across 50+ pentest types, attack surface management, and vulnerability prioritization. The NetSPI platform streamlines workflows and accelerates remediation, enabling our experts to focus on deep dive testing that uncovers vulnerabilities others miss. Trusted by the top 10 U.S. banks and Fortune 500 companies worldwide, NetSPI has been driving security innovation since 2001.
NetSPI is on an exciting growth journey as we disrupt and improve the proactive security market. We are looking for individuals with a collaborative, innovative, and customer-first mindset to join our team. Learn more about our award-winning workplace culture and get to know our A-Team at www.netspi.com/careers.
Join the mission as a Senior Security Consultant. We’re seeking a technically skilled and analytical AI/ML Penetration Tester to strengthen our cybersecurity defenses through advanced, cutting-edge testing of AI and machine learning systems. As a Penetration Tester supporting AI/ML, you will work closely with clients to deliver clear, actionable reports and contribute to the development of security best practices.
Responsibilities

Conduct engagements on AI/ML systems, web applications and API’s independently and provide technical oversight
Design and execute advanced adversarial testing (e.g., evasion, data poisoning, model extraction, inversion/inference) to expose vulnerabilities in AI/ML pipelines and architectures.
Present comprehensive penetration test findings to clients while emphasizing AI/ML risks, and collaborate on remediation strategies with model hardening, adversarial training, and threat mitigation.
Help author tools, presentations, white papers, and blog posts to share insights on AI/ML security best practices and emerging attack trends with the broader cybersecurity community. Contribute to the cybersecurity community through tools, presentations, white papers, and blogging.
Review reports for accuracy in technical oversight, perform weekly QA oversight, and provide mentoring support to others
Create, deliver, and collaborate on penetration testing reports in diverse client environments, maintaining client-specific processes, reporting standards, and access protocols to help improve their security posture
Research and develop innovative techniques, tools, and methodologies for penetration testing services, alongside commitment to improvement and execution on NetSPI specific products and processes
Participate in development, implementation, and oversight of testing, delivery, and management strategies for key client accounts
Perform administrative tasks related to day-to-day consulting activities to ensure smooth business and engagement operations.
Minimum Qualifications

Bachelor’s degree or higher, with a focus on IT, Computer Science, Engineering or Math or equivalent experience
Minimum of 3-5 years of work experience in Penetration Testing
Proficiency in using and customizing offensive toolkits for network, application, and AI/ML penetration testing
Thorough understanding of how major ML frameworks (e.g., Tensorflow, PyTorch) are implemented in real-world training and deployment pipelines.
Understanding of how to deploy AI/ML models with LangChain, including secure configuration of data flows, environment isolation, and integration with production systems
Understanding of Adversarial Machine Learning and its practical applications
Familiarity with offensive tools, based on applicable skillset (e.g., Kali Linux, Burp Suite, Metasploit, Nessus)
Familiarity with offensive and defensive IT concepts and protocols
Extensive understanding of the OWASP Top 10, MITRE ATT&CK framework, and various security frameworks.
Working knowledge of Windows, Linux and MacOS operating systems internals
Experience mentoring or coaching to growing team members, while sharing knowledge externally through blogs, hosting webinars, or presenting at conferences
Ability to work independently and as part of a team
Proficient communication skills, both written and verbal
Willingness to travel up to 5-10% minimum
This position requires an 8-hour workday, with occasional evenings or weekends necessary to meet project deadlines or critical needs
Preferred Qualifications

Ability to provide technical and QA oversight on AI/ML service line.
Comprehensive knowledge of secure AI/ML development protocols and architecture
Strong problem-solving skills and the ability to think like both an attacker and a defender.
A continuous learning mindset to keep up to date with the rapidly evolving AI/ML and cybersecurity landscapes.
Experience with model interpretability and explainability tools to understand model behavior and potential biases.
Experience in ML model development, feature engineering, and data pre-processing.
Experience in one or more of the following programming or scripting languages (e.g., Ruby, Python, Perl, C, C++, Java, and C#)
Offensive Security Certifications (e.g., GXPN, GPEN, OSCP, GWAPT)
We are an equal employment opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status or any other characteristic protected by law.