The Department of Medicine, Division of Nephrology is seeking a full-time Data Scientist IV to assist in multiple ongoing and future biomedical microscopy and artificial intelligence research projects. The successful candidate will play a critical role in designing and implementing cloud solutions and building MLOps on the cloud, as well as building CI/CD pipeline orchestration. The Data Scientist IV will also be responsible for performing data analyses, processing, and feature extraction, as well as developing data tools to accelerate research. They will also be responsible for developing and validating a variety of machine learning/deep learning models with heterogeneous cell and tissue imaging data.
In addition, the Data Scientist IV will be responsible for running code refactoring, optimization, containerization, deployment, versioning, monitoring the quality of the models, testing data science models and validating/testing automation.
The successful candidate will have the ability to communicate with a team of PhD/MS student researchers, faculty, and physicians, ensuring data and model quality, integrity, and robustness, and contributing to scientific publications related to healthcare/imaging AI research.
In summary, the Data Scientist IV will play a critical role in designing and implementing cloud solutions, building MLOps, performing data analyses and developing machine learning models. They will also be responsible for testing, validating, and monitoring the quality of the models and will work closely with a team of researchers, faculty, and physicians. This is an exciting opportunity for a highly skilled data scientist to contribute to cutting-edge research in the field of biomedical microscopy and artificial intelligence.
Essential Functions
- Maintaining a large cell and tissue microscopy image database (murine and human) as well as corresponding clinical biometrics data and outcome.
- Actively collaborate and coordinate with a large number of national and international collaborators to ingest data, and maintain the database using careful metadata standards, including sample preparation, imaging, as well digital parameters
- Maintain the derived data, such as annotations, as well as other results obtained from the raw data
- Work with collaborators, students, partners on demand and share the data as needed
- Maintain a description of data in hand as part of a database
- Maintain the data via a cloud server using Digital Slide Achieve too
- Develop and maintain end-user plugins for conducting detection, segmentation, and quantification of micro and macro anatomical structures in tissues, predictive modeling of diseases, as well as image and molecular omics data fusion
- Actively work with UF IT to ensure that the end-user customers are able to use these plugins without any service interruption. Provide needed support to end-users.
- Maintain a federated model to allow end-users to conduct computational analysis without data leaving their host servers
- Maintain a slack channel on the system, documentation, and version control for guiding end-users
- Develop and maintain tools for visualizing multi-omics data
- Actively work with UF IT to ensure that the end-user customers are able to use the visualization tool. Provide needed support to end-users.
- Maintain a slack channel, documentation, and version control for guiding end-users
- Communicating findings to project leaders and team
- Summarizing and visualizing results for inclusion in scientific publication
- Maintaining appropriate records of research methods and results and assisting in preparation of presentations and/or writing manuscripts.