Distinguished, Data Scientist

Position Summary...

What you'll do...

Role Overview:

As the Distinguished Data Scientist, you will bridge hands-on fraud data science & modeling, ML research, and governance across our fraud technology stack. You'll shape our strategy for cutting-edge fraud detection while ensuring rigorous model lifecycle practices and oversight. This role plays a critical function in making our fraud defenses both intelligent and responsible, while staying on the frontier of research-driven innovation.

Key Responsibilities:

Modeling & Production ML

· Lead the design and delivery of high-performance ML models across fraud use cases like identity verification, payment risk, returns abuse, and synthetic accounts.

· Develop hybrid decision-making systems that combine ML predictions with business logic and rules for improved precision and control.

· Ensure models are production-ready, optimized for both batch and real-time inference environments.

· Partner with engineers to define feature pipelines, scoring interfaces, and data contracts.

ML Research & Innovation

· Explore and prototype advanced ML techniques: semi-supervised learning, agentic AI, continual learning, anomaly detection.

· Collaborate with enterprise ML/AI research teams to apply foundational innovations to real-world fraud problems.

· Identify and validate new fraud signals and data sources to increase risk detection coverage.

ML Governance & Controls

· Establish governance frameworks for fairness, explainability, documentation, alerting, and drift detection.

· Build and maintain dashboards and SQL-based analytics for monitoring model health and emerging anomalies.

· Lead responsible AI practices and advise cross-functional pods on model risk management.

Cross-Functional Leadership

· Serve as the technical expert and decision-maker for modeling in pod-based execution teams.

· Collaborate with Solutions Engineering to integrate model outputs into APIs, tools, and workflows.

· Partner with Platform & Tools to ensure infrastructure supports agile modeling, experimentation, and retraining.

· Guide QA and release validation for ML components and outputs.

Mentorship & Thought Leadership

· Mentor senior data scientists, researchers, and analysts across modeling and governance.

· Lead initiatives to standardize model experimentation, evaluation, documentation, and deployment.

· Represent fraud technology in enterprise-wide forums for responsible AI and risk governance.

• PhD or Master's in Computer Science, Statistics, Mathematics, or a related field, with a strong foundation in machine learning, data science, and statistical modeling preferred, or relative work experience.
• Expertise in Fraud Detection & Risk Modeling (Preferred)
• Proficiency in building production-ready ML systems, including real-time and batch inference, feature engineering, and model optimization. Familiarity with tools like Python, SQL, Spark, and ML frameworks (e.g., TensorFlow, PyTorch, XGBoost).
• Demonstrated ability to explore and apply advanced ML techniques (e.g., semi-supervised learning, continual learning, anomaly detection) to complex problems, ideally with published work or patents.
• Deep understanding of model governance practices including fairness, explainability, drift detection, and documentation. Experience implementing responsible AI frameworks in production environments.
• Strong track record of working with engineering, product, and platform teams to integrate ML solutions into business workflows. Ability to lead technical decision-making in pod-based teams.
• Experience mentoring senior data scientists and leading initiatives to standardize modeling practices across experimentation, deployment, and monitoring.
• Ability to translate complex technical concepts into actionable insights for non-technical stakeholders and represent the team in enterprise-wide forums.