Staff AI Red Team Engineer

at  Servicenow

Company Description
At ServiceNow, our technology makes the world work for everyone, and our people make it possible. We move fast because the world can’t wait, and we innovate in ways no one else can for our customers and communities. By joining ServiceNow, you are part of an ambitious team of change makers who have a restless curiosity and a drive for ingenuity. We know that your best work happens when you live your best life and share your unique talents, so we do everything we can to make that possible. We dream big together, supporting each other to make our individual and collective dreams come true. The future is ours, and it starts with you.
With more than 7,700+ customers, we serve approximately 85% of the Fortune 500®, and we’re proud to be one of FORTUNE 100 Best Companies to Work For® and World’s Most Admired Companies™.
Learn more on Life at Now blog and hear from our employees about their experiences working at ServiceNow.
Unsure if you meet all the qualifications of a job description but are deeply excited about the role? We still encourage you to apply! At ServiceNow, we are committed to creating an inclusive environment where all voices are heard, valued, and respected. We welcome all candidates, including individuals from non-traditional, varied backgrounds, that might not come from a typical path connected to this role. We believe skills and experience are transferrable, and the desire to dream big makes for great candidates.
Job Description

JOB OVERVIEW

• We are seeking an experienced AI Red Teamer to build our AI Red Teaming capability. This critical role involves leading efforts to test and secure our AI systems, which encompass large language models and their supporting infrastructure and data. You will be at the vanguard of our defensive strategies, developing comprehensive testing protocols and coordinating with teams of internal experts to ensure our AI systems are robust against evolving threats.

QUALIFICATIONS

• Strong analytical and problem-solving skills.
• 10+ years experience as a red team or penetration testing leader, and/or a data scientist with a focus on security.
• Deep understanding of AI technologies, machine learning models, and the surrounding infrastructure.
• Familiarity with the latest threats and defense mechanisms in AI security.
• Excellent leadership and communication skills, capable of working with and coordinating multidisciplinary teams.
• Bachelor’s or Master’s degree in Computer Science, Data Science, Cybersecurity, or a related field.

PREFERRED SKILLS

• Knowledge of existing and emerging standards (e.g. EO 14110, NIST AI RMF, etc) and research in security testing of AI Systems.
• Experience in developing or securing large language models or other complex machine learning systems.

• Develop and manage our AI Red Teaming framework, including identifying potential threats, vulnerabilities, and attack vectors specific to AI and machine learning systems.
• Coordinate and lead internal teams in simulated attacks on AI systems, analyzing system responses and effectiveness of current security measures.
• Work closely with AI development teams to understand system architectures and create realistic threat models.
• Continuously update testing methodologies based on the latest research in AI security and threat intelligence.
• Prepare detailed reports on findings and recommendations, and present to senior management on regular intervals.
• Mentor and train team members on both red teaming techniques and AI system functionalities.
  Qualifications