Data Science Expert, Emerging Fraud Risk Lead

What you'll do

• Identify and mitigate emerging fraud risks for Credit Card and Lending products before they impact the business.
• Build a scalable pipeline of fraud detection and mitigation opportunities to mature the Emerging Fraud Risk capability.
• Apply machine learning, anomaly detection, and behavioral modeling to uncover evolving fraud patterns and validate risk hypotheses.
• Conduct complex investigations into fraud behaviors and translate analytical findings into actionable control recommendations.
• Serve as a bridge between monitoring and incident response teams to prioritize and address early risk indicators.
• Partner with cross-functional teams to design and implement fraud detection strategies and signal enhancements.
• Lead end-to-end analytical initiatives using large-scale structured and unstructured data to generate business insights.
• Influence strategic investment decisions and fraud risk frameworks through data-driven insights and executive presentations.

What we're looking for

• Experience in fraud analytics, data science, machine learning, or risk management, preferably within Credit Card, Lending, or Financial Services (preferred).
• Experience using Spark/PySpark to process large-scale datasets and develop scalable analytical and machine learning solutions in a production environment (preferred).
• Advanced experience using SQL, Python, and data science libraries to extract, analyze, and model large datasets for fraud detection (preferred).
• Hands-on experience developing, testing, and validating machine learning models using tools such as Scikit-learn, XGBoost, LightGBM, Pandas, and NumPy (preferred).
• Strong foundation in statistics, experimentation, and model validation (preferred).
• Proven ability to develop and deploy machine learning models and analytical solutions that identify emerging risks and drive measurable business outcomes (preferred).
• Experience applying advanced analytical techniques, including anomaly detection, predictive modeling, clustering, behavioral analytics, and network/graph analysis (preferred).
• A university/college degree is typically required, while a Master's degree or PhD is desirable (preferred).