Lead Data Scientist

Role Summary

Staples is seeking a Lead Data Scientist to join our Global Capability Center and support the Cyber Fraud Prevention organization. This senior individual contributor will design, develop, deploy, and maintain advanced analytics, machine learning models, and data products that help identify fraudulent activity, automate fraud decisions, monitor unusual customer and transaction behavior, and improve fraud operations.

This is an end-to-end applied data science role. The successful candidate will translate complex business problems into analytical solutions, prepare and model data, develop production-quality code, integrate internal and third-party services, deploy solutions, and monitor their ongoing performance.

The role requires a blend of data science, data engineering, and software engineering. It is best suited for someone who can independently take a solution from initial concept through production implementation and ongoing support.

Duties & Responsibilities

• Design, develop, validate, and operationalize machine learning and statistical models for e-commerce fraud, transaction risk, anomaly detection, customer behavior, and related use cases.

• Develop supervised and unsupervised learning solutions, including classification, risk scoring, anomaly detection, segmentation, and time-series modeling.

• Perform feature engineering using transaction, customer, payment, identity, device, product, order, and case-management data.

• Establish model baselines, validation methods, performance measures, and ongoing monitoring controls.

• Develop production-quality Python applications, data pipelines, APIs, and model-scoring processes.

• Write and optimize advanced SQL for analytical, operational, and model-development use cases.

• Design and maintain ETL and ELT pipelines that integrate data from enterprise systems, cloud platforms, fraud tools, and third-party providers.

• Build automated decisioning processes that combine model results, business rules, internal data, and external risk signals.

• Implement appropriate testing, logging, data-quality controls, exception handling, and operational alerting.

• Use Git-based source control and support code review, CI/CD, deployment, and production-support practices.

• Evaluate third-party fraud, identity, data, and machine-learning products through structured proofs of concept.

• Clearly document solution architecture, model methodology, operational procedures, assumptions, limitations, and performance.

• Partner with Fraud Operations, Cyber Analytics, engineering teams, business stakeholders, and external technology providers.

• Provide technical guidance, mentor less-experienced team members, and promote reusable development and documentation standards.