Lead Data Scientist

Introduction

The Lead Data Scientist will lead data-driven initiatives that generate actionable insights, develop predictive and statistical models, and enable data-centric decision-making across healthcare business domains.

This role will help create well-governed master data products that stakeholders and end users can trust.

As the primary subject-matter contact for entity resolution, the Lead Data Scientist will address complex data-matching challenges across large, disparate data silos and collaborate with cross-functional teams to unlock insights from healthcare datasets.

Responsibilities

• Analyze large, complex datasets to identify trends, patterns, and actionable insights.
• Develop, implement, and validate statistical and machine learning models.
• Solve enterprise-scale record linkage, deterministic and probabilistic matching, and graph-based entity resolution challenges.
• Conduct root-cause analysis on training and test data to identify and resolve model anomalies.
• Establish robust validation and testing procedures to ensure data quality, model reliability, and data integrity.
• Support model training, inference, deployment, and ongoing performance monitoring.
• Develop and refine key performance indicators to measure success across business functions.
• Establish processes for tracking, reporting, and communicating performance metrics.
• Design and build data pipelines that support semantic-layer development and stakeholder needs.
• Contribute to trusted, scalable, and well-governed master data products.

Requirements

Required Skills: Python, SQL, .

NET, AWS, Databricks, Github, Healthcare Data

Preferred Skills: Machine Learning (ML)