Senior Data Scientist

Salary: $82,500 annually

The Senior Data Scientist will support clinical research and quality-improvement initiatives within the Durham VA Cardiology through clinical informatics, biostatistics, data engineering, workflow automation, and research reporting. The incumbent will work closely with cardiologists, investigators, pharmacists, research coordinators, biostatisticians, informaticians, and operational partners to translate clinical and research questions into reliable data, rigorous analyses, and practical reporting tools.

The position will span the full analytic lifecycle, from study planning and data-source identification through extraction, processing, quality control, statistical analysis, visualization, interpretation, and dissemination. The incumbent will also help design sustainable data workflows and research infrastructure that can be adapted across current and future Cardiology studies.

• Partner with clinical investigators to define cohorts, outcomes, exposures, time windows, and data requirements for observational studies, clinical trials, implementation projects, and quality-improvement initiatives.
• Extract, integrate, transform, and curate structured clinical data from the VA Corporate Data Warehouse and other approved sources, including laboratory, medication, procedure, diagnosis, encounter, vital-sign, and longitudinal follow-up data.
• Develop reusable and well-documented data pipelines, analytic datasets, data dictionaries, validation checks, and source-to-output traceability procedures.
• Perform systematic data quality assessment, including completeness, consistency, duplicate identification, temporal validation, and reconciliation with clinical or operational source systems.

• Provide statistical programming and analytic support using appropriate descriptive, inferential, regression, longitudinal, survival, and other methods based on the study design and research question.
• Contribute to study design, feasibility assessment, analytic plans, variable definitions, sample-size considerations, interpretation of results, and sensitivity or subgroup analyses in collaboration with investigators and biostatisticians.
• Create validated tables, listings, figures, visualizations, and summary reports for investigators, sponsors, clinical teams, and leadership.
• Support preparation of protocols, abstracts, manuscripts, presentations, grant applications, and other scientific deliverables, including analytic documentation and methods sections.

• Design and maintain research data-capture, workflow, and reporting solutions using platforms such as REDCap, Power BI, SharePoint, Power Automate, and other approved tools.
• Automate processes such as patient identification, eligibility screening, task generation, follow-up scheduling, reminders, notifications, missing-data review, and escalation of overdue activities.
• Develop operational and research dashboards that track enrollment, follow-up, data completeness, clinical measures, study milestones, and other agreed performance indicators.
• Work with end users to test, document, refine, and sustain reporting tools and automated workflows while reducing unnecessary manual processing.

• Evaluate and apply advanced statistical, predictive, or machine-learning methods when appropriate to the clinical question, available data, study maturity, and validation requirements.
• Support emerging Cardiology research involving ECG, echo cardiographic, and clinical data, including development and evaluation of prediction models, while emphasizing clinical interpretability, reproducibility, and generalizability.
• Develop and implement reproducible machine-learning pipelines using ECG, echo cardiographic, and clinical data, including data preparation, quality control, model development and evaluation, validation, and reporting.
• Assess new analytic methods and data sources and recommend practical approaches that complement established clinical informatics and biostatistical workflows.

• Serve as a data-science and informatics resource for Cardiology investigators and multidisciplinary research teams, communicating technical findings clearly to clinical and nontechnical audiences.
• Apply applicable VA privacy, information-security,…