Research Data Scientist - Data Quality

Academic Staff

Regular

Data Scientist III

The Research Data Scientist – Data Quality will serve as a hands-on technical contributor responsible for developing, implementing, and operationalizing data quality capabilities within the Wisconsin Health Data Hub (WHDH) platform. WHDH is a federated funded initiative developing a secure, cloud-native data ecosystem designed to support biomedical research, advanced analytics, and AI-driven discovery using real-world health data.

This role focuses on the practical application of data science, statistical, and computational methods to assess, improve, and monitor the quality of complex clinical, biomedical, and research data. The Specialist will design and implement scalable data quality processes that identify issues related to data accuracy, completeness, consistency, validity, timeliness, and provenance across large and varied datasets. The position will develop automated quality checks, metrics, monitoring capabilities, and analytical approaches that transform complex health data into trusted, research-ready data assets.

The position requires a strong data science and analytical mindset, combined with the ability to translate research and data governance requirements into reliable, scalable solutions operating within a secure research data environment. The Specialist will work closely with data engineers, data scientists, informaticians, solutions architects, security specialists, and research stakeholders to establish repeatable data quality practices that support both current research needs and the long-term growth of the WHDH platform.

• Design, implement, and maintain scalable data quality frameworks for clinical, biomedical, and research datasets.
• Perform data profiling and exploratory analysis to identify patterns, anomalies, missingness, inconsistencies, and other data quality issues.
• Develop statistical and computational methods to assess data accuracy, completeness, consistency, validity, timeliness, and uniqueness.
• Develop and implement data quality rules, thresholds, metrics, and validation criteria appropriate for different research data sources and use cases.
• Analyze data quality trends and identify underlying causes of recurring or systemic data quality issues.
• Apply data science and machine learning techniques, where appropriate, to detect anomalies, identify potential errors, and improve data quality monitoring.

• Develop automated data validation and quality-control processes that can be integrated into WHDH data pipelines and workflows.
• Build reusable data quality components, scripts, services, and APIs to support consistent quality assessment across WHDH data assets.
• Integrate data quality checks and monitoring capabilities into cloud-based data processing and analytics environments.
• Collaborate with data engineers to embed quality controls throughout data ingestion, transformation, integration, and delivery processes.
• Develop scalable approaches for monitoring data quality across large, distributed datasets and evolving data pipelines.
• Support the implementation of automated reporting and dashboards that provide visibility into data quality metrics, trends, and remediation status.

• Collaborate with researchers, informaticians, and subject-matter experts to define data quality requirements and establish fit-for-purpose criteria for research datasets.
• Assess and improve the standardization, normalization, and harmonization of data from multiple clinical, biomedical, and research sources.
• Support the development and implementation of common data standards and controlled vocabularies to improve interoperability and consistency.
• Evaluate datasets for research readiness and identify limitations that may affect downstream statistical analysis, modeling, AI development, or other research applications.
• Support data lineage, provenance, metadata, and documentation practices that enable researchers to understand the origin, transformation, and quality characteristics of WHDH data.
• Develop reproducible methodologies and workflows for preparing high-quality datasets for research and analytical use.