Research Data Scientist – Data Quality

This is a fully remote position, open to applicants in Wisconsin.

📋 Description

• Develop, implement, and operationalize data quality capabilities within the Wisconsin Health Data Hub.

• Design and maintain scalable frameworks for data quality across clinical, biomedical, and research datasets.

• Conduct data profiling and exploratory analysis to uncover anomalies, missing data, inconsistencies, and quality concerns.

• Create statistical and computational methods, rules, thresholds, metrics, and validation criteria.

• Utilize data science and machine learning techniques for detecting anomalies and monitoring quality.

• Construct automated validation and quality control processes, reusable components, scripts, services, and APIs.

• Embed quality checks and monitoring into cloud-based data pipelines and analytic environments.

• Collaborate with data engineers, data scientists, informaticians, architects, security specialists, researchers, and stakeholders.

• Enhance data standardization, normalization, harmonization, interoperability, provenance, metadata, and documentation.

• Assess the research readiness and limitations of datasets for analysis, modeling, AI, and research applications.

• Establish data quality governance policies, standards, definitions, procedures, and accountability frameworks.

• Present findings and recommendations to both technical and non-technical stakeholders.

• Develop reproducible workflows, reports, dashboards, and tools for data quality.

• Contribute to technology transfer and sustainable adoption in academic, healthcare, and industry research settings.

⛳️ Requirements

• 3 to 5 years of professional experience in data science, research data management, data quality, data analytics, or a related technical field.

• Proficient programming skills in Python, R, and SQL.

• Experience in developing and implementing data quality processes, including profiling, validation, cleansing, standardization, anomaly detection, and quality monitoring.

• Familiarity with large-scale datasets and data processing pipelines across various structured and/or unstructured data sources.

• Capability to create automated data quality rules, metrics, validation frameworks, and monitoring processes.

• Strong analytical and problem-solving skills.

• Ability to convey complex data quality findings to both technical and non-technical audiences.

• Must either reside in Wisconsin or be willing to relocate within a reasonable timeframe.

• Continuous eligibility to work in the United States without employer sponsorship; university sponsorship, TN visas, and J-1 waivers are not available.

• A cover letter and resume are required.

• A PhD or terminal degree is preferred in Data Science, Computer Science, Statistics, Biostatistics, Biomedical Informatics, Information Systems, or a related technical field.

• Preferred qualifications include experience with clinical, healthcare, or research data; knowledge of healthcare data models and standards; familiarity with cloud environments such as Azure Synapse, MS Fabric, ADF; experience with EHR data; and expertise in reproducible data science workflows.

🏝️ Benefits

• Generous vacation, holidays, and sick leave.

• Competitive insurance options and savings accounts.

• Retirement benefits.