Associate Data Scientist

Position Overview

The Associate Data Scientist will support the development, analysis, and validation of data-driven models and analytical solutions that improve healthcare operations and patient outcomes at WVU Medicine. Working alongside data scientists, ML engineers, and clinical analysts, this role applies foundational data science and statistical skills, contributes to data pipelines and exploratory analysis, and helps translate healthcare data into meaningful insights. This is an entry-level to early-career role for candidates who have curiosity about healthcare data and how analytical insights can improve patient care.

• Bachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, or a related quantitative field AND (2) year of professional experience in data science or healthcare analytics.
• Master’s degree in a related quantitative field and one (1) year of professional experience or equivalent demonstrated through academic projects, independent work, or a portfolio in data science or healthcare data analysis, business intelligence, or healthcare reporting.

This position will require additional certification in support of the responsibilities of the position, which will be provided by WVUHS Information Technology.

• Certifications or coursework in data science, statistics, or analytics tools and platforms.
• Hands‑on experience with statistical modeling or machine learning.
• Familiarity with data visualization libraries or business intelligence tools.
• Demonstrated experience or equivalent project work writing SQL queries to extract, join, filter, and transform data from relational databases.
• Experience or equivalent project work using data to identify trends, patterns, or anomalies.

• Support data collection, cleaning, preprocessing, and exploratory analysis to prepare datasets for modeling and reporting.
• Assist in building, evaluating, and validating statistical and machine learning models using Python.
• Support data collection, cleaning, and preprocessing to ensure datasets are accurate, complete, and ready for analysis and modeling.
• Assist in feature engineering and selection by identifying, transforming, and evaluating variables from raw healthcare data. Analyze distributions, correlations, and statistical significance to surface the most relevant and reliable model inputs.
• Perform exploratory data analysis to identify patterns, trends, and anomalies in healthcare operational and clinical datasets.
• Apply foundational statistical methods including regression, classification, and clustering to analyze healthcare data and surface actionable insights.
• Support feature selection by analyzing variable distributions, correlations, and statistical significance, using techniques such as importance scoring and multicollinearity checks to identify the most relevant and reliable predictors for a given model.
• Document analytical processes, data definitions, model assumptions, and findings clearly and thoroughly.
• Participate in team ceremonies including stand‑ups, sprint planning, and project reviews.
• Monitor model and report outputs for accuracy, relevance, and drift. Evaluate findings to identify data or behavioral shifts and document insights to support retraining and improvement decisions.
• Stay current with advancements in data science, statistical methods, and analytical tools relevant to healthcare operations.
• Must pass Electronic Medical Record system proficiency or certification and continue maintaining it.

• Primarily sedentary office or remote work environment.
• Prolonged periods working at a computer workstation.

• Normal office environment or remote work setting.

• Proficiency in Python and SQL for data querying, manipulation, and basic analytical modeling.
• Foundational knowledge of statistical analysis and the ability to apply common methods such as regression, clustering, and classification to real data.
• Ability to work with structured, unstructured, balanced and imbalanced data including data cleaning, transformation, and exploratory data analysis.
• Foundational…