EcoHealth Alliance seeks a creative, dedicated, and collaborative data scientist to support analysis and reporting for COVID-19 policy response and advisory. The data scientist will work with EcoHealth Alliance team members and partner institutions to develop and maintain spatiotemporal models of COVID-19 spread and response, manage data pipelines integrating disparate large data sources, produce high-quality visualizations, reports, and dashboards and provide scientific interpretation for stakeholders.

The data scientist will report to the Principal Scientist for Computational Research and work on a team of scientists, developers, and public health professionals at an interdisciplinary health and environment focused NGO. They will participate in cross-project meetings and trainings and have opportunities to build new skills and expand their new project. They will use and build skills in R, Linux, and high-performance computing.

EcoHealth Alliance researchers largely use an R-focused analysis stack but use different languages and technologies for infrastructure based on project needs. We value growth and learning, and seek a candidate with enthusiasm to learn new skills.

RESPONSIBILITIES:

• Build, maintain and refine models of COVID-19 distribution and spread
• Create interpretable visualizations of complex models and high-dimensional and geospatial data
• Build and maintain dashboards and regular reports
• Perform rapid analyses for short-term policy advisory needs
• Refactor code to improve efficiency, simplicity, and maintainability of data handling and modeling pipelines
• Work collaboratively with interdisciplinary teams that have a mixture of workflows and needs
• Research and recommend software, hardware, and service options for tasks considering cost, usability, security, and maintainability
• Participate in the design of new projects and developing grant applications
• Contribute to open-source software projects
• Participate in other projects and tasks as required or assigned by supervisor

MINIMUM QUALIFICATIONS:

• Masters’ degree or Ph.D. in epidemiology, statistics, quantitative biological or social sciences, or related quantitative field
• Strong knowledge and experience of R for data analysis
• Experience and knowledge of at least some of
  • Linux command-line environment
  • Hierarchical, nonlinear and Bayesian statistical models
  • Working with large-scale geospatial data
• Experience using literate programming (R Markdown) and build systems to create reproducible and real-time reports and dashboards
• Demonstrated ability and willingness to rapidly learn new frameworks, technologies, and concepts
• Demonstrated ability to produce high-quality work in short time frames.
• Strong communication and teamwork skills
• Strong organizational and project management skills

OTHER DESIRED QUALIFICATIONS:

• JavaScript development experience
• Knowledge of continuous integration and cloud compute platforms