Data Software Engineer - Quality and Patient Safety initiative (QPSi)

Classification Title:

Research Software Engineer III

Job Description:

The Quality and Patient Safety initiative (QPSi) at the UF College of Medicine is seeking a Data Software Engineer to develop and maintain scalable data pipelines, enhance AI models, and support the clinical data warehouse. This role will play a key part in integrating machine learning models to improve healthcare quality and patient safety. The Data Software Engineer will collaborate with healthcare professionals, faculty, and data science teams to manage healthcare data, ensuring secure, efficient, and scalable data solutions. Key responsibilities include designing data architectures, automating workflows, optimizing databases, and ensuring compliance with healthcare data regulations. This position requires strong technical proficiency in Python (particularly the Pandas library), experience with system deployment and administration (e.g., Docker, Ansible), database management (SQL/NoSQL), and familiarity with machine learning operations (MLOps).

As part of the UF Health system, the Data Software Engineer will contribute directly to improving patient outcomes and operational efficiency by leveraging data-driven solutions to address clinical and operational challenges. Join our team and make a meaningful impact on healthcare innovation, as you collaborate with interdisciplinary teams to deliver high-impact data solutions that drive excellence in healthcare delivery.

About This Role

Feature Engineering and Data Pipeline Development

• Design, develop, and maintain scalable data pipelines to support efficient extraction, transformation, and loading (ETL) processes for large healthcare datasets.
• Design software for parallel processing of high-performance computing (HiPerGator) and high-performance data analytics workflows together with data scientists. 
• Deploy data infrastructure and systems on standard Linux servers and the HiPerGator supercomputer.
• Collaborate with data science teams and clinical domain experts to engineer new features from raw data, optimizing for predictive model performance in machine learning applications. 
• Automate repetitive data processing tasks using Python and other scripting tools to ensure consistency, reliability, and scalability of feature engineering efforts.
• Integrate data from multiple sources, ensuring data accuracy and consistency through robust validation and transformation processes.

Data Quality and Management

• Create and execute the organization’s strategy for improving and maintaining research data quality.
• With the Integrated Data Repository (IDR) team, defines and establishes data quality definitions and rules consistent with unit and organizational priorities.
• Define data quality metrics and establish processes to measure and monitor them continuously.
• Ensure compliance with quality standards.
• Support the QPSi’s data management strategy and infrastructure. 

Machine Learning Operations and Infrastructure Administration

• Implement and manage Machine Learning Operations (MLOps) frameworks to facilitate the continuous integration, deployment, and monitoring of AI models in production environments.
• Automate model deployment and updates using Docker for containerization, ensuring consistent and scalable environments across different stages of development.
• Use Ansible for infrastructure automation, managing Linux-based systems and ensuring that deployments are reproducible, and environments are consistently configured. 
• Collaborate with data scientists and UF Health IT to streamline the deployment of machine learning models, creating CI/CD pipelines for model versioning, testing, and deployment.
• Set up monitoring and logging systems to track model performance in production, and identifying and troubleshooting any issues that arise post-deployment.

Communicating Knowledge and Results

• Using software tools for business intelligence and analytics (e.g. SAP product stack), word processing, spreadsheet, presentation and organizational analyses (e.g. Microsoft Office products), provides reports of analyses to decision makers. Will also be responsible for developing reporting mechanisms via dashboards.
• Lead and contribute to developing manuscripts, abstracts and presentations for dissemination through journals, trade publications and at regional and national venues.
• Contribute to the QPSi’s education mission and its efforts to dev