The Data Science and Biostatistics Unit (DSBU) within the Department of Biomedical and Health Informatics (DBHi) collaborates with researchers across CHOP’s Research Institute to provide analysis and consultation on methods development, study design, and data analysis. This interdisciplinary team consists of biostatisticians, epidemiologists, data scientists, data analysts and other methodologists. Staff have expertise managing and using data sources and registries associated with electronic health records, clinical trials, administrative, claims, and surveys. DSBU staff have experience across various statistical methodologies, including propensity score matching, multivariate modeling, latent variable mixture models, and geographic information systems. We regularly seek mission-oriented individuals with expertise in the areas of biostatistics, quantitative methods, data science and geospatial analyses.
In order to support DSBU’s rapid growth in meeting the analysis needs of CHOP’s hundreds of research teams, we are recruiting a Data Science Supervisor. This supervisor will report to the Director of the DSBU and provide oversight for one or more analysis teams. This individual will ensure teams are fully functional and enabled to provide consistently high quality deliverables within reasonable timeframes and will collaboratively work with principal investigators from a variety of biomedical domains to strategize approaches to achieve meaningful results and academic output. In addition to traditional team and individual contributor management tasks, the supervisor will also serve in a lead analyst role on a considerable portfolio of high-profile and complex projects.
- Builds and manages a team of staff scientists in the development and execution of a high-impact data science research program.
- Recruits, hires, and manages staff, including performance management, career development.
- Collaborates with clinical and biomedical researchers to identify data science research questions in clinical and translational research.
- Leads data science research experiment planning and execution; where appropriate serves as project Principal or Co-investigator.
- Identifies relevant clinical and translational data science funding opportunities; leads collaborative proposal planning and writing.
- Disseminates research findings through peer reviewed journal articles and professional conference presentations.
- Communicates research methods, implementation, and results to varied audience of clinicians, scientists, analysts, and programmers.
- Guides and mentors junior staff and biomedical researcher collaborators in execution of research projects.
- Serves as the subject matter expert in the implementation of computational algorithms and experiments for test and evaluation as well as advanced data interpretation to assess algorithm performance.
- Sets standards and holds staff accountable for the formulation of analysis plans that meet stringent criteria for reproducibility and measures of significance.
- Serves as the subject matter expert and lead architect in the development of high-quality code implementing models and algorithms as application programming interfaces or other service-oriented software implementations.
- Plays a lead role in educating a varied audience of clinicians, scientists, analysts, and programmers on data science research methods, implementation, and results.
- Mentors junior staff, student workers, co-ops, and research trainees (fellows, post-docs).
- Manages large, complex projects and takes responsibility for major components of larger research initiatives; assigns work to junior staff, identifying, tracking, and reporting on tasks and deliverables against project timelines.
Job Responsibilities (Continued)
Job Responsibilities (Continued)
Required Licenses, Certifications, Registrations
Required Education and Experience
Required Education: Master’s degree in Analytics, Data Science, Statistics, Mathematics, Computer Science or a related field.
At least ten (10) years of experience with progressively more complex applied algorithm development, data science, applied statistics, machine learning, or mathematical modeling projects.
Preferred Education, Experience & Cert/Lic
Preferred Education: Doctoral degree in Analytics, Data Science, Statistics, Mathematics, Computer Science, or related field
Preferred Experience: Experience building and managing a technical or scientific team.
Additional Technical Requirements
- Expertise and demonstrated ability at acquiring new technical/analytic skills and domain knowledge to support successful contribution to research and development projects is required.
- Expertise formulating analysis plans and selecting appropriate methods is required.
- Expertise using existing machine learning and analytic tools such as ScikitLearn, Weka, R, and Mathematica in either applied academic or professional projects is required.
- Expertise writing code in applied academic or professional projects using one or more of the following languages: Python, Scala, Java is required.
- Familiarity with relational databases (e.g. Postgres, MySQL) strongly preferred.
- Familiarity RESTful web services application programming interfaces preferred.
- Strong verbal and written communications skills with the demonstrated ability to explain complex technical concepts to a lay audience.
- Applied statistics or mathematical modeling experience required.
- Natural language processing experience particularly in the biological and medical domains preferred.
- Experience using distributed computing technologies (e.g. Akka, MapReduce, Cuda) preferred.
- Familiarity with graph, key value, and document data stores (e.g. Neo4j, Hadoop, MongoDB) preferred.
- Experience creating informative visualizations for complex, high dimensional data preferred.
- Experience with probabilistic graphical models, time series predictive models, Markov models preferred.