Principal Engineer - Data Scientist

Wells Fargo & Company•Iselin, NJ

About The Position

About This Role: Wells Fargo is seeking a Principal Engineer in Technology as part of Cybersecurity. Learn more about the career areas and lines of business at wellsfargojobs.com. The Data-Driven Security & Analytics team at Wells Fargo is at the forefront of protecting millions of customers and billions in assets through advanced data science, machine learning, and real-time analytics. We develop production-grade models and analytical solutions that detect and prevent sophisticated fraud schemes, cyber threats, account takeovers, money laundering, insider risks, and emerging attack vectors in one of the most data-rich and heavily regulated environments in the world. Our work directly impacts real-time transaction authorization decisions, security operations, threat hunting, AML programs, and executive risk reporting. We are seeking an experienced Data Scientist to design, develop, deploy, and continuously improve machine learning and advanced analytical models that power next-generation fraud detection, cybersecurity threat detection, behavioral risk scoring, and anomaly identification. You will work on massive, high-velocity datasets—including transaction streams, authentication events, network telemetry, device fingerprints, threat intelligence feeds, and enriched behavioral profiles—while operating under strict regulatory, privacy, and security constraints. This is a high-visibility, high-impact role where your models influence billions of dollars in fraud prevention annually and help defend against nation-state-level cyber threats.

Requirements

7+ years of Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education
Strong proficiency in Python (pandas, scikit-learn, XGBoost/LightGBM/CatBoost, PyTorch/TensorFlow, PySpark) and experience with ML experimentation frameworks (MLflow, Weights & Biases, etc.).
Deep understanding of supervised & unsupervised learning, imbalanced classification, anomaly/outlier detection, time-series analysis, and ensemble techniques.
Hands-on experience deploying models into real-time production environments (e.g., via APIs, Kafka consumers, Spark Streaming, or low-latency serving platforms).
Solid SQL skills and comfort working with large-scale data warehouses/lakehouses (Snowflake, Databricks, BigQuery).
Proven track record of delivering measurable business impact (e.g., fraud loss reduction, false-positive rate improvement, detection rate lift) in regulated environments.

Nice To Haves

Experience with graph-based modeling (GraphSAGE, GNNs, link prediction) for fraud rings, money laundering networks, or lateral movement detection.
Master's or Ph.D. in Computer Science, Statistics, Machine Learning, Data Science, Applied Mathematics, or related quantitative discipline (or equivalent demonstrated experience).
Familiarity with adversarial ML, model robustness, concept drift detection, and active learning in security contexts.
Background in privacy-preserving techniques (differential privacy, federated learning, secure multi-party computation) or synthetic data generation for security use cases.
Exposure to financial crime domains: card-present/card-not-present fraud, ACH/wire fraud, mule accounts, trade-based money laundering, BEC, ransomware payments.
Knowledge of financial regulatory model risk frameworks and experience with model validation/documentation.
Publications, Kaggle rankings, or contributions to open-source ML/security projects are a plus.

Responsibilities

Act as an advisor to leadership to develop or influence applications, network, information security, database, operating systems, or web technologies for highly complex business and technical needs across multiple groups
Lead the strategy and resolution of highly complex and unique challenges requiring in-depth evaluation across multiple areas or the enterprise, delivering solutions that are long-term, large-scale and require vision, creativity, innovation, advanced analytical and inductive thinking
Translate advanced technology experience, an in-depth knowledge of the organizations tactical and strategic business objectives, the enterprise technological environment, the organization structure, and strategic technological opportunities and requirements into technical engineering solutions
Provide vision, direction and expertise to leadership on implementing innovative and significant business solutions
Maintain knowledge of industry best practices and new technologies and recommends innovations that enhance operations or provide a competitive advantage to the organization
Srategically engage with all levels of professionals and managers across the enterprise and serve as an expert advisor to leadership
Research, design, develop, and productionize machine learning models for fraud detection (supervised, unsupervised, semi-supervised), anomaly detection, behavioral biometrics, network intrusion detection, account takeover prevention, and synthetic identity fraud.
Build and maintain real-time and near-real-time scoring pipelines that deliver sub-second fraud/attack predictions during payment authorization, login, and high-risk interactions.
Perform advanced feature engineering on complex, heterogeneous data sources (transactional, temporal, graph-based, textual threat intel, device & behavioral signals) to create high-signal features for model training and inference.
Apply techniques such as graph neural networks, sequence modeling (LSTM/Transformer), ensemble methods, autoencoders, isolation forests, contrastive learning, and adversarial robustness to address evolving fraud and cyber threats.
Conduct rigorous model evaluation, explainability analysis (SHAP, LIME, counterfactuals), bias/fairness checks, and performance monitoring in production environments.
Partner closely with data engineers to define requirements for feature stores, real-time feature pipelines, and model-serving infrastructure.
Collaborate with fraud investigators, threat hunters, SOC analysts, AML teams, and product owners to translate business problems into modeling objectives and iteratively improve detection effectiveness while minimizing false positives.
Contribute to model risk management processes, model documentation, validation, and regulatory reporting (SR 11-7 / OCC guidelines, model risk frameworks).
Stay current with state-of-the-art research in adversarial ML, fraud/cybersecurity analytics, federated learning, privacy-preserving ML, and explainable AI in high-stakes domains.
Participate in model experimentation sprints, A/B testing of detection strategies, and red-team exercises simulating sophisticated attacks.