Data Scientist

About This Role

This role supports the Center of Excellence on Digital Health Innovation's research and translational mission by conducting and supporting quantitative and computational research across biomedical, clinical, and population health. The Data Scientist will design and execute rigorous analyses, advise on study design and analytical methods, and communicate findings for scholarly publications and translational decision-making. This position requires strong scientific judgment, methodological rigor, and responsible stewardship of complex health data.

Responsibilities

• Lead or substantially contribute to the design and execution of quantitative analyses for biomedical and clinical research projects
• Partner with investigators, clinicians, biostatisticians, epidemiologists, informaticians, and engineers to define scientific questions, analytic strategies, and study designs
• Evaluate the suitability, completeness, structure, and limitations of data sources prior to analysis
• Prepare, clean, harmonize, and integrate structured and unstructured data from diverse biomedical and health system sources
• Develop, implement, and validate statistical, predictive, and machine learning methods appropriate to the scientific question
• Select analytical approaches that appropriately distinguish prediction, association, and causal inference
• Evaluate model performance, calibration, robustness, generalizability, and clinical or scientific utility
• Identify and mitigate bias, confounding, missing data, measurement error, and data leakage
• Interpret results in context and communicate assumptions, uncertainty, limitations, and implications to scientific and clinical audiences
• Produce manuscripts, abstracts, presentations, technical documentation, and analytical reports
• Support reproducible research through version-controlled workflows, transparent documentation, and sound data management practices
• Contribute to responsible data governance, including privacy, security, compliance, and ethical considerations
• Advise collaborators on methodological choices and help determine when additional specialized expertise is warranted
• Stay current with advances in biomedical informatics, machine learning, and responsible AI

Requirements

• Doctoral degree, or equivalent advanced training and experience, in biomedical informatics, data science, biostatistics, epidemiology, statistics, computer science, applied mathematics, engineering, public health, or a related quantitative field
• Demonstrated record of independent or highly substantive contributions to biomedical, clinical, public health, or life sciences research
• Advanced expertise in at least one primary quantitative area, such as: Data science or machine learning, Biostatistics, Epidemiology, Biomedical or clinical informatics
• Strong working knowledge of biostatistics and epidemiologic principles, including study design, statistical inference, bias, confounding, missing data, and interpretation of observational and experimental data
• Proficiency in Python, R, or another statistical programming language
• Proficiency in SQL and experience working with relational or analytical databases
• Experience designing, implementing, and validating quantitative analyses using real-world biomedical data
• Ability to evaluate model performance, calibration, and validity using methods appropriate to the research question and intended use
• Demonstrated ability to communicate complex technical findings clearly to multidisciplinary scientific and clinical audiences
• Experience producing reproducible analyses with clear documentation of methods, assumptions, and results

Nice to have:

• Experience leading or co-leading research projects in academic, clinical, or translational settings
• Record of peer-reviewed publications, conference presentations, or grant-supported research
• Experience with electronic health records, claims data, registries, clinical trials, genomic data, imaging data, sensor data, or other complex biomedical datasets
• Experience with longitudinal data analysis, survival analysis, causal inference, or observational research
• Experience developing or evaluating machine learning models in biomedical or clinical settings
• Familiarity with natural language processing, large language models, or unstructured clinical text
• Experience with cloud computing, distributed data platforms, or high-performance computing
• Experience deploying analytical workflows, research tools, or decision-support systems
• Familiarity with healthcare data standards and terminologies such as FHIR, ICD, SNOMED CT, LOINC, or OMOP
• Knowledge of privacy, fairness, explainability, and responsible AI in healthcare
• Experience mentoring trainees, junior analysts, or multidisciplinary collaborators

Important Details

• Application deadline: 02/01/2027

About the Company

The Department of Medicine’s Center of Excellence on Digital Health Innovation conducts and supports quantitative and computational research across biomedical, clinical, and population health. This work provides the scientific and methodological foundation for the responsible design, development, validation, and deployment of artificial intelligence and machine learning solutions, including clinical algorithms and medical diagnostic tools intended to improve clinical research, care delivery, and patient outcomes.