Principal AI Security Engineer

Citizens Financial Group•Johnston, RI

9d•Hybrid

About The Position

The Principal AI Security Engineer works with engineering teams and architecture to produce high-quality technology solutions, with autonomy to lead, design, and develop innovative solutions to major technical challenges in banking. The role is a peer-leader pursuing cutting-edge initiatives and solutions across Citizens’ operations. The engineer builds and operationalizes security controls for AI-powered applications, protecting models, prompts, and outputs from misuse and abuse throughout the AI lifecycle, from data ingestion and training through deployment and runtime. The role secures AI integrations, identities, data, infrastructure, and third-party services; monitors AI systems for anomalies and malicious activity; integrates security testing into development pipelines; and leads incident response for AI-related events. The position follows a hybrid schedule of four days onsite and one day remote per week at one of the listed hubs. Remote-only work is not available.

Requirements

At least 8 years of working experience in data-intensive applications or data engineering.
Experience implementing large-scale technology enhancements or pivots, including pilot implementation and analysis.
Excellent understanding of AI/ML patterns and techniques.
Excellent understanding of DevOps.
Understanding of Python and at least one other programming language.
Experience with IT infrastructure and cloud development.
Experience with APIs.
Experience designing highly available and resilient solutions, automation, and identifying performance improvement opportunities.
Bachelor’s degree or foreign equivalent in computer science or a related field.
Experience in two or three of these technology areas: infrastructure, security, DevOps, application development, database technologies, or cloud computing.

Nice To Haves

Working experience in the financial services industry.
Bachelor’s degree in computer science, computer engineering, or a related discipline.
Executive speaking and presentation skills, including formal presentations, whiteboarding, and presentations to large and small groups.
Preferred degree in software engineering, computer science, engineering, mathematics, or a related discipline.

Responsibilities

Collaborate with engineering and architecture teams on solution design, contributing insight while supporting product success and adherence to enterprise architecture principles.
Design, modify, develop, and implement software solutions, including modern components, tools, and applications aligned with strategic business goals.
Incorporate scalability, manageability, and maintainability into distributed service-based system designs.
Use industry best practices to evaluate, remediate, and prevent vulnerabilities during software development.
Serve as a peer leader who encourages innovation and accountability.
Build and operationalize security controls for AI-powered applications to help models, prompts, and outputs withstand misuse and abuse.
Secure the AI lifecycle from data ingestion and model training through deployment and runtime across internal applications and external platforms.
Engineer safeguards against AI threats including 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, including databases, APIs, and 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.
Monitor AI systems and agentic behaviors for anomalies, policy violations, and malicious activity using logging and detection engineering practices.
Harden cloud infrastructure supporting AI workloads, including containers, orchestration platforms, and serverless services.
Evaluate and manage risks from third-party AI SaaS solutions, including data handling, access control, and vendor security posture.
Integrate automated security testing into AI development pipelines, including adversarial testing and model robustness validation.
Lead incident response for AI systems, investigating misuse, security-related model drift, and potential data exposure.
Collaborate with architects, developers, and governance teams to align AI security practices with business objectives and regulatory requirements.