NetSPI
Senior Security Consultant (AI/ML Penetration Testing)
NetSPI, California, Missouri, United States, 65018
Senior Security Consultant (AI/ML Penetration Testing)
Job Category:
Services Requisition Number:
SENIO001590 Apply now Posted: July 25, 2025 Full-Time Remote Locations
Showing 1 location Canada Toronto, ON M5J2T3, CAN Description
This is a remote position, and candidates must be located in Ontario, CA. NetSPI provides proactive security solutions to discover, prioritize, and remediate security vulnerabilities, helping businesses protect what matters most. Our services include Penetration Testing as a Service (PTaaS), External Attack Surface Management (EASM), Cyber Asset Attack Surface Management (CAASM), and Breach and Attack Simulation (BAS). We leverage a combination of security experts, innovative processes, and advanced technology to deliver clarity, speed, and scale in cybersecurity. We are experiencing growth and seek collaborative, innovative, and customer-focused individuals to join our team. Learn more about our culture at www.netspi.com/careers. Join us as a Senior Security Consultant. We are looking for a skilled AI/ML Penetration Tester to enhance our cybersecurity defenses by testing AI and machine learning systems. You will work closely with clients to deliver actionable reports and contribute to security best practices. Responsibilities
Conduct engagements on AI/ML systems, web applications, and APIs independently, providing technical oversight. Design and execute advanced adversarial testing (e.g., evasion, data poisoning, model extraction, inversion/inference) to identify vulnerabilities in AI/ML pipelines and architectures. Present findings to clients, emphasizing AI/ML risks, and collaborate on remediation strategies such as model hardening and adversarial training. Author tools, white papers, and blog posts to share insights on AI/ML security and attack trends with the cybersecurity community. Review reports for accuracy, perform weekly QA, and mentor team members. Create and deliver penetration testing reports tailored to client environments, adhering to their processes and standards. Research and develop new techniques, tools, and methodologies for penetration testing services. Participate in developing and overseeing testing strategies for key client accounts. Perform administrative tasks to support consulting activities. Minimum Qualifications
Bachelors degree or higher in IT, Computer Science, Engineering, Math, or equivalent experience. 3-5 years of experience in Penetration Testing. Proficiency with offensive toolkits for network, application, and AI/ML testing. Knowledge of ML frameworks (e.g., TensorFlow, PyTorch) in real-world scenarios. Understanding of deploying AI/ML models with LangChain, including security considerations. Knowledge of Adversarial Machine Learning and related tools. Familiarity with offensive tools like Kali Linux, Burp Suite, Metasploit, Nessus. Understanding of IT concepts, security frameworks, and operating systems (Windows, Linux, MacOS). Experience mentoring or coaching team members and sharing knowledge externally. Ability to work independently and in teams. Strong communication skills, both written and verbal. Willingness to travel 5-10%. Availability for an 8-hour workday with occasional evenings/weekends. Preferred Qualifications
Ability to provide technical and QA oversight for AI/ML services. Knowledge of secure AI/ML development protocols and architecture. Strong problem-solving skills with attacker and defender perspectives. Continuous learner mindset for evolving AI/ML and cybersecurity landscapes. Experience with model interpretability, explainability, and bias detection. Experience in ML model development, feature engineering, and data pre-processing. Proficiency in programming/scripting languages like Python, Ruby, Perl, C, C++, Java, C#. Offensive Security Certifications (e.g., GXPN, GPEN, OSCP, GWAPT). We are an equal opportunity employer. All qualified applicants will receive consideration without regard to race, color, religion, sex, national origin, disability, veteran status, or other protected characteristics. #J-18808-Ljbffr
Job Category:
Services Requisition Number:
SENIO001590 Apply now Posted: July 25, 2025 Full-Time Remote Locations
Showing 1 location Canada Toronto, ON M5J2T3, CAN Description
This is a remote position, and candidates must be located in Ontario, CA. NetSPI provides proactive security solutions to discover, prioritize, and remediate security vulnerabilities, helping businesses protect what matters most. Our services include Penetration Testing as a Service (PTaaS), External Attack Surface Management (EASM), Cyber Asset Attack Surface Management (CAASM), and Breach and Attack Simulation (BAS). We leverage a combination of security experts, innovative processes, and advanced technology to deliver clarity, speed, and scale in cybersecurity. We are experiencing growth and seek collaborative, innovative, and customer-focused individuals to join our team. Learn more about our culture at www.netspi.com/careers. Join us as a Senior Security Consultant. We are looking for a skilled AI/ML Penetration Tester to enhance our cybersecurity defenses by testing AI and machine learning systems. You will work closely with clients to deliver actionable reports and contribute to security best practices. Responsibilities
Conduct engagements on AI/ML systems, web applications, and APIs independently, providing technical oversight. Design and execute advanced adversarial testing (e.g., evasion, data poisoning, model extraction, inversion/inference) to identify vulnerabilities in AI/ML pipelines and architectures. Present findings to clients, emphasizing AI/ML risks, and collaborate on remediation strategies such as model hardening and adversarial training. Author tools, white papers, and blog posts to share insights on AI/ML security and attack trends with the cybersecurity community. Review reports for accuracy, perform weekly QA, and mentor team members. Create and deliver penetration testing reports tailored to client environments, adhering to their processes and standards. Research and develop new techniques, tools, and methodologies for penetration testing services. Participate in developing and overseeing testing strategies for key client accounts. Perform administrative tasks to support consulting activities. Minimum Qualifications
Bachelors degree or higher in IT, Computer Science, Engineering, Math, or equivalent experience. 3-5 years of experience in Penetration Testing. Proficiency with offensive toolkits for network, application, and AI/ML testing. Knowledge of ML frameworks (e.g., TensorFlow, PyTorch) in real-world scenarios. Understanding of deploying AI/ML models with LangChain, including security considerations. Knowledge of Adversarial Machine Learning and related tools. Familiarity with offensive tools like Kali Linux, Burp Suite, Metasploit, Nessus. Understanding of IT concepts, security frameworks, and operating systems (Windows, Linux, MacOS). Experience mentoring or coaching team members and sharing knowledge externally. Ability to work independently and in teams. Strong communication skills, both written and verbal. Willingness to travel 5-10%. Availability for an 8-hour workday with occasional evenings/weekends. Preferred Qualifications
Ability to provide technical and QA oversight for AI/ML services. Knowledge of secure AI/ML development protocols and architecture. Strong problem-solving skills with attacker and defender perspectives. Continuous learner mindset for evolving AI/ML and cybersecurity landscapes. Experience with model interpretability, explainability, and bias detection. Experience in ML model development, feature engineering, and data pre-processing. Proficiency in programming/scripting languages like Python, Ruby, Perl, C, C++, Java, C#. Offensive Security Certifications (e.g., GXPN, GPEN, OSCP, GWAPT). We are an equal opportunity employer. All qualified applicants will receive consideration without regard to race, color, religion, sex, national origin, disability, veteran status, or other protected characteristics. #J-18808-Ljbffr