Data Scientist

Develop predictive agronomic models to address scientific challenges in precision agriculture; query, munge,
manipulate & explore complex agronomic datasets; evaluate & resolve geospatial and agricultural data quality
issues; build data processing pipelines; collect & engineer features and apply machine learning, process
modeling & statistical modeling techniques for model development; select modeling & data visualization methods;
write research code & libraries with automated tests; collaborate with cross-functional stakeholders to deliver
research findings; provide coaching & training in agile framework and methodologies; coordinate sprints,
retrospective meetings & stand-ups.

Requires Master’s in Data Science, Statistics, Applied Mathematics, or closely-related quantitative field & 3 yrs experience building predictive machine learning and statistical models for
research applications; writing code in Python with data science packages, including Pandas for data aggregation; using Numpy, Matplotlib and/or Seaborn for data analysis & visualization;
using Sklearn & XGboost for machine learning and modeling; using TensorFlow and/or Keras for deep learning modeling; conducting exploratory data querying, manipulation & analysis to
evaluate data trends; applying statistical & machine learning techniques on a scalable platform to real-world applications; working with large, complex datasets using SQL & PySpark; using
version control systems, including Git, to track code history; joining large & diverse datasets across multiple databases and performing data quality checks; communicating with technical &
non-technical stakeholders at all levels of the organization, including business stakeholders, peer groups and team members; and deploying code to a scalable cloud-based platform,
including AWS, GoogleCloud and/or Azure. Telecommuting permitted from home office location anywhere in the U.S.