Principal AI Security Engineer

Locations & Work Arrangement: Remote is not an option, candidates must be willing to commute to one of the following hub locations with a hybrid schedule of 4 days onsite and 1 day remote per week with flexibility in one of the following hubs:

• Phoenix, AZJohnston, RIBoston, MAFranklin, TNWestwood, MAPittsburgh, PACharlotte, NCIrving, TXCleveland, OHPhiladelphia, PAMarlton, NJThe Principle Security Engineer will be responsible for:
• Collaborating and contributing insight to solution design ideation, ensuring both the success of the product and adherence to enterprise architecture principles.
• Designing, modifying, developing and implementing software solutions. Building modern, architecturally sound components, tools and applications to meet mission-driven strategic business goals.
• Infusing quality of service characteristics, such as scalability, manageability and maintainability, into distributed service-based system designs
• Employing industry best practices to evaluate, correct and prevent vulnerabilities during the software development process.
• Serving as a peer-leader, encouraging a culture of innovation and accountability
• Build and operationalize security controls that protect AI-powered applications, ensuring models, prompts, and outputs are resilient against misuse and abuse.
• Focus on securing the full AI lifecycle—from data ingestion and model training to deployment and runtime—across both internal applications and external platforms.
• Engineer safeguards against emerging AI threats such as prompt injection, data poisoning, model inversion, and unintended data leakage.
• Strengthen identity and access controls for AI systems, including service identities, API protection, and least-privilege access across SaaS and cloud environments.
• Secure integrations between AI components and enterprise systems (databases, APIs, SaaS tools) to prevent unauthorized access and data exfiltration.
• Protect sensitive data used by AI systems through encryption, tokenization, and privacy-preserving techniques across hybrid and cloud-native architectures.
• Continuously monitor AI systems and agentic behaviors for anomalies, policy violations, and malicious activity using logging and detection engineering practices.
• Harden cloud infrastructure that supports AI workloads, including containers, orchestration platforms, and serverless services, ensuring secure configurations.
• Evaluate and manage risks associated with third-party AI SaaS solutions, focusing on data handling, access control, and vendor security posture.
• Integrate automated security testing into AI development pipelines, including adversarial testing and validation of model robustness.
• Lead incident response efforts related to AI systems, investigating misuse, model drift with security implications, and potential data exposure events.
• Collaborate cross-functionally with architects, developers, and governance teams to align AI security practices with business objectives and regulatory requirements.

Required: Bachelor's degree

Preferred: Degree in Software Engineering, Computer Science, Engineering, Mathematics or related discipline Pay Transparency The salary range for this position is $150,000 to $190,000 per year, plus an opportunity to earn additional incentive earnings. Actual pay is based on various factors including, but not limited to, the budget, work location, and relevant skills and experience.

Benefits: Comprehensive benefits include medical, dental, and vision coverage, retirement plans, parental leave, flexible work arrangements, education reimbursement, wellness programs, and generous paid time off exceeding local requirements.

Citizens Benefits Overview: For an overview of our benefits, visit our Careers site: Citizens Benefits Overview.

Equal Employment Opportunity: Citizens, its parent, subsidiaries, and related companies (Citizens) provide equal employment and advancement opportunities to all colleagues and applicants for employment without regard to age, ancestry, color, citizenship, physical or mental disability, perceived disability or history or record of a disability, ethnicity, gender, gender identity or expression, genetic information, genetic characteristic, marital or domestic partner status, victim of domestic violence, family status/parenthood, medical condition, military or veteran status, national origin, pregnancy/childbirth/lactation, colleague's or a dependent's reproductive health decision making, race, religion, sex, sexual orientation, or any other category protected by federal, state and/or local laws. At Citizens, we are committed to fostering an inclusive culture that enables all colleagues to bring their best selves to work every day and everyone is expected to be treated with respect and professionalism. Employment decisions are based solely on merit, qualifications, performance and capability.