BlueConduit, a water analytics social enterprise, pioneered the predictive modeling approach to lead service line identification and replacement. Through our Platform-as-a-Service offering, utilities, municipalities, government agencies, and consultants standardize, predict, report, and communicate key information about lead pipes. BlueConduit was founded in 2019 and operates out of Ann Arbor, MI.
Our service offering enables utilities to focus their resources on digging where the lead is. Digging in the right place accelerates the removal of this significant health concern and saves millions of dollars in avoided digs. Since 2016, BlueConduit has worked with more than 200 cities and inventoried over 2 million service lines, saving our customers over $300M and years of added work.
BlueConduit is hiring a data scientist, who will use machine learning models to predict health hazards in infrastructure. Our founding team members were first to build models to predict whether water pipes were made of lead in Flint. And we’ve expanded that to serve cities throughout North America, on both a for-profit and charitable basis. We are passionate about using data science for social good and improving equity.
- Build and improve machine learning models and data pipelines
- Actively engage in R&D to identify how to continue to scale the impact of BlueConduit’s predictive methods
- Integrate client data into internal software tools, generating predicted probabilities of likelihood of lead in pipes at any address
- Support clients with data analysis
- Participate and present in the BlueConduit Data Seminars (with internal, industry, and academic speakers)
This role will report to the Director of Data Science.
We are a small, remote, and growing team, so this is an excellent opportunity to grow into and shape your role at our company. The role provides opportunities for mentorship, growth and for stepping into leadership positions.
- Experience building data science products at a company/organization that is scaling and growing quickly
- Undergraduate degree in quantitative field (e.g., CS, math, stats, physics, etc.)
- Substantial experience with Python, especially Pandas, Scikit-learn, PySpark, and Numpy
- Extensive experience with machine learning and statistical models, including validation and evaluation of model performance
- Experience working with geospatial models and modern GIS systems (e.g., GeoPandas)
- Familiarity with issues related to modeling (e.g., selection biases, causal inference)
- Excellent data visualization skills and ability to present results clearly to non-technical
- Excellent verbal and written communication skills
- Attention to detail
- Be curious to learn and will value the human side of data science
- Be passionate about data science for social good and environmental justice
- Graduate degree in quantitative field
- Experience using distributed computing to fit your data science needs (eg. PySpark)
- Experience building cloud-based models for tracking and version-controlling (e.g. on Databricks)
- Proficiency with Git workflow
- Experience with Agile product development (e.g., sprints, standups, scrums)
- Familiarity with infrastructure water quality, or government data
- Salary range ($120-135K), depending on level of experience
- Stock options
- Health benefits
- Simple IRA benefit
- Co-working space/work place stipend