Lead Data Scientist

We are seeking a Lead Data Scientist to drive the design, development, and implementation of advanced fraud detection analytics and machine learning solutions. This is a hands‑on technical leadership role responsible for building predictive models, developing innovative analytic approaches, and delivering actionable insights that identify fraudulent activity, uncover hidden relationships, and support investigative teams.

The ideal candidate has extensive experience leading data science initiatives within fraud detection, financial crimes, investigations, or risk analytics environments. They will combine expertise in machine learning, graph analytics, natural language processing, and data engineering to build scalable analytical solutions that improve fraud detection capabilities.

• Lead the design, development, testing, validation, and deployment of advanced fraud detection models and analytical solutions.
• Develop predictive, prescriptive, and anomaly detection models using machine learning and AI techniques.
• Design and implement sophisticated data matching, entity resolution, and identity linkage methodologies.
• Conduct link analysis to identify relationships between individuals, organizations, transactions, and events.
• Build interactive dashboards and visualizations that communicate complex fraud patterns to business stakeholders and investigators.
• Develop and optimize analytical workflows using Azure Databricks and SQL Server.
• Perform rigorous model testing, validation, and quality control to ensure accuracy, reliability, and explainability.
• Collaborate with investigators, business partners, and technical teams to translate business problems into scalable analytical solutions.
• Leverage graph databases and graph analytics using Neo4j to identify hidden connections and organized fraud networks.
• Integrate Robotic Process Automation (RPA) capabilities to automate fraud detection and investigative processes.
• Apply Natural Language Processing (NLP) techniques to analyze structured and unstructured data sources.
• Continuously evaluate emerging AI, machine learning, and advanced analytics technologies to improve fraud detection effectiveness.
• Mentor junior data scientists and provide technical leadership throughout the model development lifecycle.
• Document methodologies, model assumptions, validation results, and technical recommendations.

• Bachelor's degree in Data Science, Computer Science, Statistics, Mathematics, Engineering, or a related technical discipline. Master's degree preferred.
• 8+ years of experience in data science, advanced analytics, or machine learning.
• 5+ years of hands‑on experience developing fraud detection, financial crime, risk, or investigative analytics solutions.
• Demonstrated experience designing analytical approaches from concept through implementation.
• Proven experience managing model development, testing, validation, and quality assurance efforts.
• Strong proficiency with:
• Microsoft SQL Server
• Power BI
• Neo4j Graph Database
• Strong programming experience with Python and SQL.
• Experience building and deploying machine learning models in production environments.
• Experience with:
• Entity resolution and data matching
• Link analysis
• Natural Language Processing (NLP)
• Artificial Intelligence (AI)
• Robotic Process Automation (RPA)
• Strong understanding of supervised and unsupervised learning techniques, anomaly detection, clustering, classification, and predictive modeling.
• Experience working with large, complex, structured and unstructured datasets.
• Excellent analytical, problem‑solving, and communication skills.

• Experience supporting government, financial services, healthcare, insurance, or law enforcement fraud investigations.
• Experience with graph analytics and network analysis for identifying organized fraud schemes.
• Familiarity with cloud-based data engineering and MLOps best practices.
• Experience working in Agile development environments.
• Knowledge of explainable AI (XAI), model governance, and responsible AI principles.

The successful candidate will lead the development of cutting‑edge fraud detection capabilities by combining advanced analytics, AI, machine learning, graph analytics, and automation to identify complex fraud patterns, improve investigative efficiency, and deliver scalable, high‑quality analytical solutions that drive measurable business impact.