Data Science Intern

SB Energy is a fast‑growing renewable energy company that designs, builds, and operates large solar and storage projects. We offer summer internships to students and recent graduates in a dynamic and innovative environment. Benefits of an SB Energy Internship Apply skills and knowledge learned in the classroom to on‑the‑job experiences Comprehensive, value‑added project(s) Work in teams and with cross‑functional colleagues in a professional environment Develop technical skills specific to your major Gain opportunities for professional development by building relationships and learning from industry professionals in a live business environment Final project summary presentation to the team About the Data Science Intern The Data Science Intern will be responsible for creating an automated pipeline to benchmark our energy forecasting model performance periodically, thereby enabling continuous improvement in predictive accuracy and operational efficiency. The intern will also develop and implement machine learning models for forecasting, with a focus on ISO load forecasting and wind generation forecasting. Responsibilities Design and implement an automated pipeline that benchmarks the performance of weather and energy forecasts from various sources, including data ingestion via APIs, data quality identification and processing, data cleaning, and development of metrics for accuracy, reliability, and efficiency. Apply backtesting/validation methods to assess forecast model performance using different date ranges, events, and scenarios (Monte‑Carlo simulation) in historical data. Utilize machine learning algorithms to create accurate and reliable ISO‑wide or regional load forecast and wind generation forecasts. This involves collecting and processing historical weather and wind generation data, selecting appropriate ML models, training the models, and continuously improving their accuracy, while conducting comprehensive data analyses to identify patterns, trends, and anomalies. Evaluate forecasting model performance using statistical methods. Skills and Experience Bachelor’s degree (ongoing) in computer science, data science, mathematics, statistics, or a related field. Experience with Python and basic libraries for machine learning such as scikit‑learn and pandas. Experience with machine learning and deep learning frameworks such as XGBoost, PyTorch, or Keras. Experience with cloud‑based ML AI services. Experience using frameworks to automate, accelerate, and sustain the machine learning lifecycle. Location Redwood City, CA. Hybrid office and remote work setup. #J-18808-Ljbffr