Expert Data Scientist, Fraud Risk Detection

This is a fully remote position, open to applicants in United States.

📋 Description

• Conduct extensive analysis of large datasets to explore and develop fraud labeling.

• Detect patterns of fraud, methods of attack, and behavioral indicators.

• Convert ambiguous fraud and risk challenges into clear hypotheses, analytical strategies, model specifications, and measurable success criteria.

• Create machine learning models aimed at detecting fraud related to account openings, account takeovers, and identity risks.

• Assess models utilizing metrics such as ROC/AUC/KS/Gini, precision/recall, fraud capture rate, false-positive rate, customer impact, and fraud losses averted.

• Develop and validate predictive features leveraging identity, transactional, consumer credit history, device, behavioral, temporal, velocity, network, and third-party data.

• Produce clean, efficient, and thoroughly tested Python and PySpark code.

• Collaborate with teams to implement models and features in batch, retro, or real-time decision-making environments.

• Oversee feature quality, model performance, shifts in population, and changes in fraud patterns.

• Design and deliver analyses that cover model behavior, trade-offs, risks, and recommendations.

• Adhere to standards regarding data privacy, model documentation, explainability, validation, and governance.

• Report directly to the Senior Manager of Fraud Analytics.

• Partner with senior data scientists and engineers throughout the process from problem identification to feature engineering, experimentation, and deployment.

⛳️ Requirements

• Minimum of 3 years of experience in data science, machine learning, statistical modeling, or a related quantitative field.

• Bachelor's or advanced degree in computer science, statistics, engineering, data science, or another quantitative area.

• Hands-on experience in developing models for fraud detection, identity risk, credit risk, financial crime, or other adversarial risks.

• Proven ability to create significant fraud-related features.

• Strong proficiency in Python and PySpark.

• Experience in writing modular and tested code applicable to large datasets and distributed or cloud data systems.

• Familiarity with tools such as pandas, NumPy, scikit-learn, XGBoost, TensorFlow, or similar technologies.

• Understanding of supervised learning, model evaluation, feature selection, statistical inference, experimentation, and model calibration.

• Experience dealing with class imbalance, delayed or incomplete labels, evolving attack patterns, and model drift.

• Proven track record of transitioning models from experimental phases to production.

• Compliance with relevant work authorization and employment regulations in the United States.

🏝️ Benefits

• Competitive compensation package along with a bonus plan.

• Essential benefits including medical, dental, vision, and a matching 401K.

• Flexible work arrangements, with options for remote, hybrid, or in-office work.

• Generous time-off policy that includes volunteer time off, vacation, sick leave, and 12 paid holidays.

• Comprehensive benefits overview.

• Opportunities for variable pay.

• An inclusive, purpose-driven culture.

• Support for accommodations related to disabilities or special needs.