The role

As a socially-driven Data Scientist, you will be contributing to UrbanFootprint’s suite of geospatial data products, many of which leverage our parcel level map of all properties across the US that integrates information about people, employment, land use, the environment and more.  These data products power nearly every decision our customers make.  They allow our customers to design environmentally conscious growth plans, target government relief dollars, and promote equitable community development.  

As a product-minded and empathetic Data Scientist, you care deeply about how data quality and accuracy impact real decisions.  You are autonomous, not independent;  you incorporate ideas and feedback from stakeholders and other data scientists, clearly communicate progress and are accountable for the validity and accuracy of the models you build and the outputs you ship.  You are comfortable researching on your own and asking for help when you need it.  You’re thoughtful; you ask questions to ensure you understand the why and verify that UrbanFootprint is tackling the right problems and taking the right approaches.  Pragmatic and hands on, you are comfortable applying models and algorithms to real world scenarios.  You are comfortable prototyping solutions and eager to work with others to ship your models to production.

As a Series B funded startup, UrbanFootprint is an ideal fit for someone with an entrepreneurial spirit who is comfortable with (or, even, energized by) moving forward through ambiguity, lightweight process, and the inevitable changes in direction that come with iterating and refining on product-market fit.

What you’ll do:

• Collaborate with product managers and data scientists to understand the problems our customers face and how we can best solve them.
• Build prototype solutions addressing a wide range of real-world problems and work with data engineers to transform those prototypes into real products.
• Partner with urban planning domain experts, customer success and product managers to ensure that model accuracy meets customer needs and expectations. 
• Communicate project progress, challenges and outcomes to internal stakeholders.

Your background most likely includes:

• Work experience equivalent to a Master’s degree or higher in Statistics, Data Science or Machine Learning.
• Experience with a variety of statistical or machine learning regression and classification models, missing data imputation, and/or clustering algorithms.
• High proficiency in Python and Python’s scientific programming stack such as pandas, sklearn, statsmodels, one neural network library, and one data visualization library.
• Experience developing models in an iterative, fast-paced environment. 
• Excellent communication, collaboration, and documentation skills.

Bonus qualifications:

• Experience with geospatial modeling such as spatial clustering and spatial clustering with non-spatial attributes, spatial interpolation, and small area estimation and/or spatial downscaling techniques.
• Experience as a full-stack data scientist, owning data pipelines, model development and production model implementation.
• Familiarity with large-scale, cloud-based data analysis frameworks including BigQuery, Xarray, Pangeo, SQL, Apache Beam, Dask or PySpark.
• You are socially driven to leverage data to facilitate a more equitable and resilient society.