Lead Data Scientist

About the role

Mastercard is seeking a Lead Data Scientist to drive the design, delivery, and success of data science initiatives on the merchant/acquiring side of the business. The role focuses on building production‑ready machine‑learning solutions that address merchant risk, fraud detection, credit risk, anti‑money‑laundering, and payment‑related risk use cases.

Key responsibilities

• Design, build, evaluate, enhance, and monitor machine‑learning and statistical models for merchant risk, fraud detection, credit risk, AML, and payment‑related risk.
• Oversee feature engineering, model training, validation, packaging, production support, and performance monitoring across the full model lifecycle.
• Ensure high standards for model quality, robustness, interpretability, documentation, and production reliability.
• Lead hands‑on model development, experimentation, and technical problem solving using large‑scale merchant and transaction data.
• Partner with product, engineering, QA, customer success, and business stakeholders to define problem statements, success metrics, implementation needs, and release readiness.
• Collaborate with AI/ML engineering and development teams to support model deployment, scaling, operationalization, and ongoing implementation.
• Operate independently in a lean, highly collaborative team, driving initiatives end‑to‑end with limited oversight while balancing speed, quality, and production impact.
• Deliver work through typical project cycles of approximately 4–6 weeks from development through delivery.

Required profile

• Deep technical expertise in data science and machine‑learning with end‑to‑end project ownership.
• Strong production focus and experience delivering production‑ready ML solutions.
• Cross‑functional leadership and ability to work with product, engineering, and business teams.
• Ability to operate independently in a collaborative environment and drive initiatives with limited oversight.
• Experience handling large‑scale transaction and merchant data.

Required skills

• Machine learning
• Statistical modeling
• Feature engineering
• Model lifecycle management (training, validation, packaging, monitoring)
• Large‑scale data handling
• Collaboration with AI/ML engineering teams