Data Scientist / Engineer

Responsibilities

• Design and implement the methodology for tracking and quantifying changes in federal data streams
• Build and maintain data pipelines to collect, clean, and monitor federal datasets and agency changes over time
• Develop maps and geospatial tools that overlay environmental, socioeconomic, and weather data to show government change in local context
• Support pilot site selection analysis using data-driven metrics such as need, capacity, and historical monitoring gaps
• Document methodology and findings for use in public reports, mapping products, and partner-facing tools
• Evaluate and integrate new data sources and technical tools as program needs grow
• Take on other technical tasks as needed to advance the work

Skillset

Required

• Approximately 3–5 years of professional experience building and maintaining data pipelines, or equivalent demonstrated skill
• Proficiency in Python for data collection, cleaning, analysis, and pipeline development (e.g. pandas, requests, working with APIs)
• Working knowledge of SQL and database design for organizing large or evolving datasets
• Experience with mapping and geospatial tools such as Mapbox, ArcGIS, QGIS, PostGIS, or similar
• Fluency with version control (Git) and reproducible, well-documented workflows
• Excellent written and verbal communication, including the ability to explain technical decisions to non-technical colleagues and community partners

Nice to have

• Experience with federal or other government open data sources (e.g. EPA AQS or AirNow, NOAA, Census/ACS)
• Familiarity with cloud platforms and data hosting (e.g. AWS, Google Cloud)
• Data visualization skills for translating technical findings into public-facing maps and reports
• Experience incorporating LLMs or other machine learning into internal tooling or analysis workflows
• Background or coursework in environmental science, public health, or environmental justice, or prior work with community-based organizations