Data Scientist III

About the role

As a Data Scientist III at Moffitt, you will work directly with key stakeholders throughout the organization to document data-related needs and identify novel approaches—including advanced data science and analytics techniques—to address those needs. Your work will integrate into Moffitt’s broader Health Data Services and Digital Innovation strategies.

You will collaborate with clinical and research faculty focused on genomics, radiomics, immuno-oncology, evolutionary therapy, patient-reported outcomes, and other areas to ensure Moffitt’s analytics methods maximize the value of its vast data assets. This includes optimizing data formatting, lineage, quality, linkages, and visualizations as new data types—such as medical record text, radiology and pathology images, molecular data, and patient-generated data (wearables)—are incorporated into Moffitt’s cloud-based analytics platform.

Your responsibilities will include implementing Moffitt’s data and analytics strategy through predictive modeling, algorithm development, dataset manipulation to identify trends, and data mining solutions using natural language processing (NLP) and machine learning. Your work will impact both clinical use cases (e.g., tumor boards) and cutting-edge research (e.g., automation of tumor segmentation).

Responsibilities

• Document data-related needs and propose advanced analytics solutions to address them.
• Collaborate with clinical and research faculty to align analytics methods with Moffitt’s data assets.
• Optimize data formatting, lineage, quality, linkages, and visualizations for new and existing data types.
• Develop predictive models and algorithms to extract meaningful insights from large datasets.
• Implement data mining solutions using NLP, machine learning, and other advanced techniques.
• Support clinical and research initiatives, including tumor boards and automated tumor segmentation.
• Lead complex analyses for peer-reviewed publications, scientific abstracts, and presentations.
• Serve as a scientific collaborator with multidisciplinary research teams.
• Contribute to competitive grant applications by developing statistical analysis plans, study designs, sample size calculations, and methodology sections.
• Prepare and contribute to manuscripts for publication in peer-reviewed journals.
• Work with large multi-institutional, registry-based, or real-world healthcare datasets.

Requirements

• Bachelor’s degree in data science, mathematics, statistics, computer science, or a related quantitative field (required).
• Master’s or PhD in Biostatistics, Epidemiology, Statistics, Data Science, or a related quantitative discipline (preferred).
• Bachelor’s degree + 5+ years of experience in quantitative analytics and applied data science OR Master’s/Doctorate + 3+ years of experience in quantitative analytics and applied data science.
• Strong programming skills in AI/ML, Natural Language Processing (NLP), and statistical modeling applications.
• Advanced proficiency in R and experience with Python, SQL, and modern data visualization tools (e.g., matplotlib, ggplot2, plotly).
• Experience writing SQL queries, mining large datasets (e.g., pandas, dplyr), and creating data visualizations.
• Experience leading analyses for peer-reviewed publications, scientific abstracts, and presentations.
• Experience collaborating with investigators and multidisciplinary research teams.
• Experience supporting grant applications through statistical analysis plans, study design, and methodology development.
• Demonstrated experience contributing to or leading manuscript preparation for peer-reviewed journals.
• Experience working with large multi-institutional, registry-based, or real-world healthcare datasets.

Pay

Salary range: $108,492.80 – $165,422.40. Actual compensation may vary based on location, experience, skills, education, and internal equity.