Data Scientist Intern

Summit Utilities, Inc. is a natural gas utility focused on providing safe, reliable, and clean-burning natural gas service. The Data Scientist Intern will support data science solutions for utility operations through data exploration, feature engineering, model development, validation, visualization, and communication of analytical findings.

What you'll do:

• Assist in building, validating, and iterating statistical, machine learning, and optimization models supporting natural gas demand forecasting, weather normalization, asset health and preventative maintenance, field operations optimization, and customer segmentation
• Support exploratory data analysis, data profiling, and feature engineering across work order, weather and climate, SCADA, pipeline telemetry, billing, and gas usage data
• Contribute to model development pipelines in Microsoft Fabric and assist with data quality checks and validation of model inputs and outputs
• Develop clear visualizations and quantitative summaries, and document analytical logic, data sources, and assumptions for the team
• Complete an assigned project and present the results to the AI and Enterprise Data teams and leadership

What they're looking for:

• Currently enrolled in a bachelor's or master's degree program in Data Science, Statistics, Mathematics, Operations Research, Computer Science, Engineering, or a related quantitative field
• Coursework, academic projects, or prior internship experience involving statistics, machine learning, or quantitative analytics
• Exposure to the model development process — data preparation, feature engineering, training, and evaluation
• Familiarity with cloud data platforms such as Microsoft Fabric, Azure, Snowflake, or Databricks are a plus but not required
• Working knowledge of Python for data analysis (pandas, NumPy, scikit-learn, matplotlib/seaborn) and foundational SQL skills
• Understanding of core statistical and machine learning concepts, including regression, classification, model validation, and evaluation metrics
• Coursework or interest in time-series analysis and forecasting methods; exposure to techniques such as ARIMA or Bayesian methods a plus
• Willingness to learn Microsoft Fabric notebooks and Lakehouses and collaborative development practices (Git, Azure DevOps)
• Strong communication skills, intellectual curiosity, and a friendly, solution-oriented approach aligned with Summit's values
• Rising junior or senior undergraduate standing, or current graduate enrollment, preferred

Benefits:

• Medical benefits
• Dental benefits
• Vision benefits
• Other benefits that provide flexibility, choice, and support to employees
• Benefits designed to support employees at work and at home