Sr. Data Scientist, Specialty Networks Solutions

Specialty Networks is an integrated, multi-specialty organization with GPOs, Life Sciences, and Research solutions in Urology, Oncology, Gastroenterology, and Rheumatology. Specialty Networks solutions include population health management, patient engagement, clinical research, and workflow automation technologies to achieve Center of Excellence status in Standards of Care, Clinical Research, Practice Operations, and Value-based Care. Specialty Networks leverages the Power of its Network, represented by over 10,000 providers, to help independent physician practices, industry, wholesalers/distributors, payers, and policymakers improve patient outcomes.

What Data Science contributes to Cardinal Health

The Data & Analytics Function oversees the analytics lifecycle in order to identify, analyze and present relevant insights that drive business decisions and anticipate opportunities to achieve a competitive advantage. This function manages analytic data platforms, the access, design and implementation of reporting/business intelligence solutions, and the application of advanced quantitative modeling.

Data Science applies base, scientific methodologies from various disciplines, techniques and tools that extracts knowledge and insight from data to solve complex business problems on large data sets, integrating multiple systems.

Job Summary

The Sr. Data Scientist in Specialty Networks Solutions leads the design, hardening, and deployment of high-impact real-world data (RWD) products and advanced analytical solutions for biopharmaceutical partners. Acting at the intersection of clinical informatics, data engineering, and biopharma client strategy, this individual is directly responsible for ensuring clinical data quality, optimizing data availability, and unlocking measurable commercial and clinical value for life sciences clients. The role requires deep domain expertise across healthcare data ecosystems (electronic health records, medical/pharmacy claims, specialty pharmacy dispensing, lab registries), sophisticated quantitative and machine learning capabilities, and a rigorous engineering approach to transforming prototype analyses into resilient, production-grade data products.

Data Governance & Standards

Define governed definitions for the highest-priority derived variables

Set Quality Control rules for each transformation step in datasets, profile the raw and transformed data hands-on, and trace anomalies to root cause

Document the pipeline and data model, including the decision logic at each transformation step

Harden data assets and analytical pipelines to ensure production reliability, regulatory defensibility, and reproducibility across client-facing deliverables

Engineering Partnership

Assess engineering delivery meets client and quality requirements, and close gaps (e.g., order data not flowing into deliverables)

Run a shared request queue for questions from clients and internal analysts, and track each item with engineering

Identify key growth areas from the market to enhance data pipelines both in structured and unstructured data sources

Prioritize workflows to deliver more value through product generation

Accelerate data accessibility by standardizing common data models (e.g., OMOP, clinical registries) and enabling rapid extraction of fit-for-purpose real-world evidence (RWE)

Client & Strategic Partnership

Join discovery conversations alongside the delivery team, and build prototype dashboards on real data (e.g., a patient journey) as the specification for engineering