Data Scientist III

Data Scientist III

Company: University of Florida
Location: Gainesville, FL, United States
Job Type: Full-Time, Time-Limited
Salary: $82,000 – $95,000

About Us

The University of Florida is a leading public research institution committed to advancing knowledge and innovation across disciplines. The Department of Medicine’s Division of Nephrology Quantitative Health focuses on integrating clinical, imaging, and molecular data to improve patient outcomes. The Computational Microscopy Imaging Lab (CMIL) is at the forefront of multimodal AI research, developing predictive models of disease progression using advanced data science methods. Learn more about our initiatives at University of Florida.

Key Duties

The Data Scientist III will serve as the Clinical Text & EHR Data Lead, supporting federally funded, interdisciplinary research projects. Core responsibilities include:

• Designing and maintaining NLP pipelines to extract structured information from clinical notes using tools such as MedSpaCy or cTAKES.

• Engineering structured EHR features, including labs, medications, and diagnoses, while ensuring semantic consistency with standards like OMOP and FHIR.

• Integrating longitudinal patient data with imaging and biopsy records for time-resolved analysis and AI model development.

• Troubleshooting data gaps, alignment issues, and conflicts while maintaining high standards for reproducibility and analytic traceability.

• Collaborating with institutional data providers, research teams, and external partners to ensure secure, accurate data transfers.

• Providing informal guidance to junior analysts or student researchers and recommending new analytic methods to improve pipeline performance.

Requirements

• Bachelor’s degree in data science, statistics, bioinformatics, analytics, or related field with 5 years of experience; or Master’s with 3 years; or Doctoral with 1 year.

• Proven experience in NLP within the clinical domain and structured EHR data handling.

• Familiarity with Python and data integration tools.

• Strong organizational skills and attention to reproducibility and version control.

• Ability to communicate effectively and collaborate with interdisciplinary teams.

Preferred:

• Experience with MedSpaCy, cTAKES, OMOP, FHIR standards.

• Prior work in clinical or research environments with multimodal datasets.

• Additional technical certifications (e.g., AWS, Security+) are a plus but not required.

Pay & Benefits

• Salary range: $82,000 – $95,000 per year.

• Opportunity to work on cutting-edge, federally funded research projects.

• Collaborative environment with mentorship and professional growth opportunities.

See full job details on the company site