Principal AI Red Team Reseacher

When you join Verizon Verizon is one of the world’s leading providers of technology and communications services, transforming the way we connect around the world. We’re a human network that reaches across the globe and works behind the scenes. We anticipate, lead, and believe that listening is where learning begins. In crisis and in celebration, we come together—lifting up our communities and... striving to make an impact to move the world forward. If you’re fueled by purpose, and powered by persistence, explore a career with us. Here, you’ll discover the rigor it takes to make a difference and the fulfillment that comes with living the #NetworkLife. Verizon Cybersecurity (VCS) is looking for an AI Security Researcher. You will be responsible for developing and executing cybersecurity research across all parts of the Machine Learning Operations (MLOps) life cycle, including reading, understanding, and operationalizing threat research related to attacks on AI/ML systems. The successful candidate will possess an effective aptitude in understanding expert perspectives on both AI and cybersecurity topics such as application development, adversarial machine learning, model development, vulnerability reporting, and security testing in efforts to support VCS and broader Verizon goals. What you’ll be doing... • Conducting comprehensive analysis of AI/ML threats and vulnerabilities, profiling emerging security research, and developing novel testing procedures. • Executing realistic attack scenarios to assess the resilience and detection capabilities of internal systems and processes. • Developing scripts, tools, or methodologies to enhance AI test and evaluation processes. • Assessing and evaluating AI/ML-related architecture and technology solutions for their security posture. • Developing and implementing advanced detection mechanisms for AI/ML threats. • Refining and optimizing detection rules, signatures, and alerts in collaboration with other cybersecurity teams. • Briefing security leadership on the latest AI/ML security developments through written and verbal communications. You’ll need to have: • Bachelor’s degree or six or more years of experience. • Four or more years of relevant work experience • One or more years of AI security testing, adversarial machine learning, or AI purple team experience. Even better if you have one or more of the following: • Experience teaching or educating others about adversary machine learning, AI/ML security, or purple teaming. • Experience building content around AI security for senior leadership. • Experience with security tools such as Burp Suite. • Knowledge of the OWASP Top 10 for LLMs project and/or MITRE ATLAS • Solid understanding of Machine Learning Operations (MLOps) processes and technologies, from data gathering and model development to operational deployment. • Ability to leverage Jupyter Notebooks, Shell scripts, or programming languages like Bash, Python, or Go to automate simple tasks. • Ability to think critically and creatively to solve complex security problems. If Verizon and this role sound like a fit for you, we encourage you to apply even if you don’t meet every “even better” qualification listed above. This role is eligible for the Department of Defense Skillbridge Program. Where you’ll be working In this remote role, you'll work from home with occasional in-person trainings and meetings. Scheduled Weekly Hours 40 Equal Employment Opportunity We’re proud to be an equal opportunity employer - and celebrate our employees’ differences, including race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, and Veteran status. At Verizon, we know that diversity makes us stronger. We are committed to a collaborative, inclusive environment that encourages authenticity and fosters a sense of belonging. We strive for everyone to feel valued, connected, and empowered to reach their potential and contribute their best. Check out our diversity and inclusion page to learn more Apply Job!