Data Scientist II

Job Summary

The College of Public Health/Public Health Analytics and Informatics is seeking a Data Scientist II to design, develop, and deploy data science and machine learning solutions and assist in the implementation of data engineering infrastructure for public health analytics, including the Rapid Actionable Data for Opioid Response in KY (RADOR-KY) project. This position will build data science solutions and predictive models for time series forecasting systems related to risk prediction, outcome forecasting, and population health analytics, while designing and maintaining data pipelines for both batch and streaming data processing.

The ideal candidate will write complex SQL queries, assist in the development and monitoring of ETL workflows, and support interactive dashboards and geospatial visualizations to communicate results to stakeholders. Responsibilities include implementing data science solutions, model validation frameworks and results, optimizing database queries and pipeline performance, integrating multiple data sources, and maintaining comprehensive technical documentation for data science, ML models, and data processes.

This role requires advanced data science and machine learning expertise, proficiency with Python ML libraries, strong SQL programming skills, experience with data pipeline orchestration tools, and the ability to translate analytical needs into technical solutions. This position may supervise and mentor junior data scientists with SQL and Python/R development. The position may be fully remote.

• Design, develop, and deploy data science and machine learning solutions for public health analytics.
• Assist in the implementation of data engineering infrastructure for analytics projects.
• Build data science solutions and predictive models for time series forecasting related to risk prediction, outcome forecasting, and population health analytics.
• Design and maintain data pipelines for both batch and streaming data processing.
• Write complex SQL queries and assist in the development and monitoring of ETL workflows.
• Support interactive dashboards and geospatial visualizations to communicate results to stakeholders.
• Implement data science solutions and model validation frameworks; report results.
• Optimize database queries and pipeline performance; integrate multiple data sources.
• Maintain comprehensive technical documentation for data science, ML models, and data processes.
• Potentially supervise and mentor junior data scientists with SQL and Python/R development.
• Position may be fully remote.

Statistical programming expertise (R or SAS) required.

No

Required

Education:

MS. Preferred Education/

Experience:

MS with experience or PhD in Biostatistics, Epidemiology, Computer Science, or Data Science.

03/03/2026

We value the well-being of each of our employees and are dedicated to creating a healthy place for everyone to work, learn and live. The University of Kentucky is a Tobacco & Drug Free campus. The University follows federal and state nondiscrimination laws and provides equal opportunities for qualified persons in all aspects of institutional operations and does not discriminate on the basis of race, color, national origin, ethnic origin, religion, creed, age, physical or mental disability, veteran status, uniformed service, political belief, sex, sexual orientation, gender identity, gender expression, pregnancy, marital status, genetic information or socio-economic status.

Any candidate offered a position may be required to pass pre-employment screenings as mandated by University of Kentucky Human Resources, which may include a national background check and/or drug screen.