The role

As the Senior Data Scientist leading Climate Risk and Community Resilience, you will be driving the evolution of UrbanFootprint’s risk-based data products including Grid Resilience Insights and Municipal Bonds Insights.  These products are designed to help asset managers and financial institutions make investment decisions by taking into account climate and environmental hazard risk, community impacts and vulnerability, and physical infrastructure and the built environment.  These data products leverage our parcel-level map of all properties across the US to facilitate decision-making for scales ranging from parcels and neighborhoods to states and the entire US.

As a product-minded and pragmatic data science leader, you know how to appropriately scope projects to ensure we are delivering what customers need today, and have ideas for how we can improve in the future.  You are autonomous, not independent;  you work collaboratively with business partners to understand the ‘what’ and ‘why’ and take full ownership of figuring out ‘how’ to meet those needs.  You proactively communicate progress and are accountable for the validity and accuracy of all models produced for your data products.  You are a hands-on leader, able to build models and provide technical support and mentorship to junior data scientists.  

What you'll do: 

• Partner with product managers to develop and execute on a technical roadmap for our Climate Risk and Resilience data products.
• Develop novel models and algorithms to help our customers face society’s pressing challenges of climate vulnerability and social inequity across multiple verticals.
• Identify, normalize, and analyze various environmental and climate hazard datasets to assess where risks are the highest.
• Partner with solutions analysts, customer success and product managers to help turn customers problems into actionable solutions.
• Help to define and communicate a quantified understanding of risk across multiple products.
• Own data science problems end-to-end, from ideation, exploratory data analysis and prototype, to collaborating with data engineers and machine learning engineers to ship models to production.

Your background most likely includes:

• Work experience equivalent to a Master’s degree or higher in Statistics, Data Science, or a branch of Environmental Sciences/GeoSciences, with experience working with geospatial (raster and vector) or spatiotemporal data
• Fluency in Python and Python’s scientific programming stack such as pandas, GeoPandas, rasterio, xarray, sklearn, pytorch, fastai, statsmodels and various visualization packages including map-based visualizations.
• Practical experience with a wide variety of statistical and machine learning models such as statistical and machine learning regression models, geostatistics, downscaling and interpolation.
• Experience developing models in an iterative, fast-paced environment.
• Excellent communication, collaboration, and documentation skills.

Bonus qualifications: 

• Master’s degree or higher in Statistics, Data Science, Computer Science, Civil or Environmental Engineering, GeoSciences, or Urban Planning (with an emphasis on geospatial, spatiotemporal or machine learning modeling), or other similar technical fields.
• Experience working with publicly available climate and hazard data, including downscaled CMIP5 datasets (e.g., LOCA/MACA), NOAA flood hazard layers, and others.
• Experience developing quantitative impact estimates of climate change or extreme weather events such as infrastructure damage estimates, economic impacts and/or population impacts. 
• Deep experience with and knowledge of geospatial modeling and analysis including familiarity with raster rescaling, joining rasters to vector features, and spatiotemporal modeling.
• Experience as a full-stack data scientist, owning data pipelines, model development and production model implementation.
• Familiarity with large-scale data analysis frameworks including SQL, Apache Beam, Dask or PySpark.
• Passion for climate resilience, equity, urban planning, and leveraging data to facilitate a more equitable and resilient society.