AI Data Scientist

The University of Pittsburgh School of Health and Rehabilitation Sciences (SHRS) is a nationally renowned leader in the field of health care education, research, and clinical practice preparation. With 14 different disciplines related to health and rehabilitative care, SHRS shapes future generations of health care professionals—therapists, counselors, advocates, scientists, providers, and practitioners—trained to serve the needs of all people regardless of background, levels of health, or mobility. We are built on a legacy of academic excellence and innovation and fueled by passionate educators and researchers, allowing us to meet the health care and rehabilitation needs of today and drive meaningful change in the future. Learn how bold moves SHRS. https://www.shrs.pitt.edu/about/how-bold-moves-shrs

The University of Pittsburgh School of Health and Rehabilitation Sciences (SHRS), in partnership with Pitt’s Department of Biomedical Informatics (DBMI), is seeking a data scientist to oversee a large, complex data set, the Rehabilitation Datamart With Informatics Infrastructure for Research (ReDWINE). ReDWINE draws electronic medical records data from UPMC’s extensive clinical and payor systems and organizes it for analysis by rehabilitation scientists. The data scientist will work under the direction of Dr. Yanshan Wang, Associate Professor, to utilize advanced programming methods for raw data extraction and aggregation, statistical analysis, and document programming to create analytic data files. He/she will be part of a larger team of SHRS research leaders and Pitt informaticists and information technologies specialists who collaborate on ReDWINE’s development and management. The preferred candidate must have a master’s degree, a strong interest in academic research, and experience in managing large data sets, performing statistical analysis, documentation, and reporting.

Experience and knowledge of skillsets weighted more heavily

Experience with database design, database programming skills, SQL skills

Experience designing ETL solutions

Expert in one or more programing languages (Java and Python preferred)

Experience with data model design, data standards, ontology design is a plus

Experience with data warehousing, Hadoop/data lake platform implementation is a plus

Experience with IT platform implementation in a technical and analytical role is a plus

Experience of writing, submitting, and publishing scientific articles

Oversees large, complex data sets and utilizes advanced programming methods and statistical software for raw data extraction and aggregation, statistical analysis, and document programming to create analytic data files. Creates statistical reports; assists with manuscripts, grants, and regulatory submissions. Maintains data infrastructure and tracks data assets. Adheres to all protocols.

The candidate will design, implement, and maintain the IT infrastructure using enterprise-level Java programming language. Requires experience in Java, SQL, and infrastructure system design.

Ability to track and finish project milestones, research data warehouse development, and report to the stakeholders.

Responsible for leading the clinical data retrieval, data analysis activities will be conducted using customized Python programming language. In addition, the candidate will also summarize the results in scientific articles and submit to academia conferences and journals.

The candidate will communicate with several stakeholders, including rehabilitation researchers to understand the demands, the Pitt internal R3 office to understand the Neptune data warehouse operation, and health informatics faculties for the overall strategy.

Little physical effort required. Duties are primarily sedentary. May be required to move objects up to 25 pounds occasionally.