EcoHealth Alliance - Research Data Scientist, Disease Forecasting

Paid / New York City or Remote (working US EST hours) / Full-time

EcoHealth Alliance seeks a Research Data Scientist to work closely with our computational science team on reproducible research in disease ecology and forecasting. This is a key position at a rapidly growing NGO with diversely funded scientific research programs around the world focused on conservation and zoonotic disease emergence. The Research Data Scientist will work on multiple projects, developing forecast models for disease spread via travel and trade, early-stage outbreak forecasting, and early warning signals of disease emergence. They will also support building internal tools such as R packages and data pipelines and contribute to open-source projects.

EcoHealth Alliance uses a reproducible data science tool stack that includes R, {targets}, {renv}, {tidyverse} and {tidymodels}, git/GitHub, Docker (Rocker), GitHub Actions, AirTable, Open Data Kit, Dolt, and Stan. We build interpretable models, using frequentist and Bayesian methods, generalized mixed linear and additive models, and machine-learning models such as boosted and Bayesian additive regression trees. A successful candidate will have experience with some of these tools and methods and/or equivalents, and a demonstrated ability to learn and adopt new tools.

This position is based in New York City with a remote (including international) option. Visa sponsorship and moving expenses are available for hires to move to work primarily in-office. Remotes hires must be available to collaborate with team members via email, chat, and video calls during US EST business hours and be available as needed to coordinate with collaborators in other international time zones. The position will require regular travel to the New York office several times per year for a remote candidate.

Description and Responsibilities

Reporting to the Senior Data Scientist and Principal Scientist, the Research Data Scientist will :

  • Build machine-learning models using frequentist and Bayesian methods for insight, prediction, and use in production
  • Analyze, visualize, and summarize complex, high-dimensional data and model outputs to extract insights and trends and communicate these to diverse audiences
  • Build reproducible pipelines for data collection, processing, and quality control
  • Support the development of internal and open-source R packages and tools
  • Produce high-quality data visualizations and written reports/manuscripts on data science and modeling project outputs, targeting audiences with a wide range of technical knowledge
  • Work with EcoHealth Alliance scientists to develop new scientific research projects and research proposals on pandemic preparedness and emerging disease ecology
  • Engage openly and respectfully with EcoHealth Alliance scientists and partners across multiple projects as required and at all project stages, from development to implementation to publication/communication
  • Present work and represent EcoHealth Alliance at conferences and scientific meetings and in outreach to current and potential collaborators, donors, and other audiences
  • Perform other tasks as assigned by supervisor


Minimum Qualifications

  • Master’s degree or PhD in data science, statistics, ecology, epidemiology, or a related field, or B.A. or B.S. and 3+ years relevant experience. Data science or programming “bootcamp” training will be considered with sufficient experience
  • Strong R programming skills, including processing high-dimensional data (including geospatial data), producing reproducible reports (R Markdown/Quarto), developing automated pipelines (targets/drake/make), visualization, and writing R packages
  • Experience applying machine learning techniques to answer research questions
  • Experience with version control (git) and command-line tools.
  • Demonstrated ability to self-teach new methods and tools
  • Strong project management skills, including proven ability to work independently and manage multiple projects and deadlines while working with multiple teams
  • Excellent interpersonal and written and verbal communication skills, including the ability to document methods and results and communicate effectively with colleagues
  • Positive attitude towards solving complex problems
  • Strong sense of team spirit and cultural sensitivity
  • Fluency in English

Additional Desired Qualifications

  • Experience in Shiny app development, development of interactive dashboards
  • Experience in the processes of reproducible and open scholarly research
  • A record of scientific publications

Applications are due January 15, 2023.

More details at

Apply to this position

Apply via form at You will be asked to upload a PDF of a cover letter and CV/Resume, totaling no more than 4 pages.

This topic was automatically closed after 31 days. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.