Responsibilities

Duties of the Environmental Data Scientist will include the following:

• Data organization: organize, catalog, and structure heterogeneous environmental and geospatial datasets using consistent metadata and controlled vocabularies, with clear provenance, so they can be combined consistently and reproducibly.
• Analytical logic: help define how rules and analytical logic are represented, versioned, and evaluated against layered datasets, with traceable analytical lineage from inputs to results.
• Data product design: define what analytical inputs and outputs should contain, including data, results, and metadata, the schemas that represent them, and how those schemas evolve over time.
• Domain reasoning: bring environmental and hydrologic domain knowledge to bear on how data is weighted, interpreted, and encoded into rules.
• Validation & QA: develop checks, test cases, and validation logic to confirm that rules produce correct, explainable, and consistent results.
• Documentation & collaboration: document data schemas, analytical logic, and data sources; collaborate across the Science, Engineering, and Platform teams to keep the system understandable, accessible, and maintainable.

The Environmental Data Scientist selected should have the following:

• Master's in environmental science, ecosystem science, water resources, hydrology, earth science, environmental data science, or a related field; or a Bachelor's plus 2 years applying data science to environmental problems; or equivalent hands-on experience.
• Strong environmental and data science background, with the ability to reason about how environmental evidence should be represented and combined.
• Proficiency in a data science language such as R or Python for data wrangling, analysis, and modeling.
• A working sense of geospatial data science, including experience with GIS tooling and spatial datasets (e.g., R, ArcGIS, QGIS, Google Earth Engine).
• Comfort thinking structurally about data schemas, inputs, and outputs, and translating domain logic into clear, testable rules.
• Strong technical and scientific writing skills.

The Ideal Environmental Data Scientist will have the following:

• Experience designing data schemas, structured formats, or APIs, and defining inputs and outputs for downstream consumers.
• Familiarity with rules-based or decision-support systems and how to make their logic transparent and explainable.
• Experience integrating multiple public and agency data sources (e.g., USGS, NOAA, PRISM) for watershed or environmental analysis.
• Exposure to machine learning or statistical modeling applied to environmental data.
• Track record of scientific writing, publication, or open-source contribution.
• Colorado Front Range presence for periodic in-person collaboration.