Lead Data Engineer - Data Scientist

About this role: Wells Fargo is seeking a Lead Data Engineer in Cybersecurity as part of Identity Access Management. Learn more about career areas and business divisions at wellsfargojobs.com This role sits at the intersection of cybersecurity, data science, machine learning, and AI. The successful candidate will develop intelligent solutions that improve access governance, identify anomalous behavior, automate entitlement decisions, and generate actionable insights across Wells Fargo's Identity and Access Management ecosystem. In this role, you will: Lead complex initiatives with broad impact and act as key participant in large scale software planning for the Identity and Access management. Design, develop, and run tooling to discover problems in data and applications and report the issues to engineering and product leadership Apply knowledge of statistical and data science methods and techniques to business problems relating to Identity and Access Management. Serve as a subject matter expert on ML, AI and the application of mathematical and statistical techniques to large datasets. Design, support and operate data pipelines, data models, dashboards, and API integrations to deliver real-time and batch analytics use cases. Design and conduct experiments, statistical analyses, and hypothesis testing to evaluate proposals in support of controls, policies, and operational processes. Build AI-powered capabilities that identify inappropriate access, recommend entitlements before users request them, and detect anomalous behavior across millions of identity events. Lead other IAM team members including operations, onboarding, initiatives and engineering teams as well as line of business and lines of defense teams to understand analytical needs and translate them into technical solutions. Establish and implement engineering and analytical best practices when developing solutions. Develop solutions in accordance with established security, privacy, model risk, and regulatory guidelines. Develop, test, deploy and support of ML-enabled analytical solutions and guide other members of the team in ML, AI and statistical techniques in driving adoption of AI/ML across IAM. Assist in monitoring model health, reliability, and drift to ensure continuous improvement and required remediation. Demonstrate proficiency in using AI ‑ assisted development and analysis tools (e.g., GitHub Copilot and approved code ‑ centric agents) Leverage AI to accelerate system design, coding, testing, analysis, and troubleshooting Apply strong technical judgment when validating and integrating AI ‑ assisted outputs into solutions Understand and account for model limitations, security risks, and operational considerations Apply AI responsibly in development and production environments Ensure AI usage aligns with security, compliance, privacy, and ethical standards Required Qualifications: 5+ years of Database Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education 5+ years of experience with Python data science libraries such as Pandas, NumPy, and Scikit-Learn, together with exposure to a deep learning framework such as TensorFlow or PyTorch Desired Qualifications: Knowledge of Vertex AI, GCP environments, BigQuery and getting models into production on these platforms Knowledge of graph networks for anomaly detection (Neo4j) A learning mindset that keeps up-to-date with the latest developments in the field Knowledge of Github for code management, Power BI, Tableau, Alteryx Understanding of software engineering fundamentals including testing, debugging, code reviews etc is highly desirable Knowledge of the mathematical foundations of statistics, machine learning, and modern AI techniques. Strong understanding of model evaluation techniques, particularly for classification and clustering models including metrics such as precision, accuracy, F1-scores,