Full-Time Health Data Scientist @ Boston, Massachusetts, U.S.
The Department of Biostatistics at the Harvard T.H Chan School of Public Health invites applications for a Health Data Scientist position to work on software tools for environmental health policy. The work will involve close collaboration with Drs. Corwin Zigler, Francesca Dominici, and Christine Choirat. The successful candidate will also interact with PhD and postdoctoral students. A special focus will be on the design and implementation of scalable software tools and reproducible workflows.
The ideal candidate is an independent, solution-oriented thinker with a strong background processing large data sets, applying analytical rigor and statistical methods, and driving toward actionable insights and novel solutions.
Duties and Responsibilities:
- The Data Scientist will contribute to the effort of retrieving (via web scraping or REST APIs) and leveraging massive amounts of data (for example, Medicare, Census, EPA Air Quality System, and atmospheric transport and dispersion model outputs) to study the health impacts of air pollution regulations.
- The Data Scientist will contribute to the efforts of the team in terms of statistical software development, software dissemination, and reproducible research.
- The Data Scientist will provide high-quality implementations of quantitative models and will also write, and contribute to writing, scientific articles and research proposals. The successful candidate will help developing and maintaining R packages and datasets, and creating innovative web-based data visualizations.
- Masters degree in Statistics, Biostatistics, Computer Science, Data Science, or other quantitative field.
- Strong background in applied statistics and computational methods.
- Interest in open-source software, reproducibility and data management.
- PhD in Statistics, Biostatistics, Computer Science, Data Science, or other quantitative field.
- Demonstrated ability to contribute to research of new statistical approaches, inference algorithms, and machine learning techniques.
- Familiarity with multiple data science tools (R, Shiny, GIS, d3, Python, SQL,…), and ability to learn new tools as required.
- Experience in creating and maintaining R packages.
- Experience in handling very large (spatial) datasets is highly desirable.
- The position is funded for one year with strong possibility of renewal.
- URL: https://www.hsph.harvard.edu/biostatistics/fellowship-opportunities/#datascience.
- We also have two other openings: https://www.hsph.harvard.edu/biostatistics/fellowship-opportunities/#dominici_bigdata, https://www.hsph.harvard.edu/biostatistics/fellowship-opportunities/#env_hlth.