Machine Learning Analyst Intern

The Machine Learning Analyst Intern will perform modelling tasks for energy load forecasting. They will be responsible for the development, iteration, and optimization of bespoke machine learning and statistical models. The intern will also assist in data ingestion, validation, and transformation, developing end-to-end pipelines to support modelling efforts.

Core responsibilities will include:

• Analysis of geospatial weather datasets and load data to perform feature engineering, regression, and statistical diagnostics;
• Design and implementation of statistical and machine-learning models for load forecasting, focusing on stability, performance, and reliability;
• Creation of end-to-end pipelines for predictive analytics using Python, SQL, and Google Cloud.

The Intern may also be requested to assist with general administrative and management support functions to improve operations at Lightshift Energy. The ideal candidates for this position will have a strong quantitative mind.

Location:

• Arlington, VA headquarters but may make exceptions for candidates finishing a degree program.

Compensation & Benefits:

• Hourly compensation provided commensurate with experience;
• Possible bonus incentives for successful project work.

Required Qualifications:

• Pursuing a degree in engineering, computer science, math, statistics, data science or related field from an accredited university;
• Experience with data management, analytics and coding (SQL, R, Python, Excel);
• Experience developing statistical time-series models (e.g., ARIMA/ARIMAX, multivariate linear regression) for forecasting applications;
• Experience developing and validating machine learning models for time-series forecasting (e.g., regularized regression, tree-based methods, neural networks);
• Strong written and verbal communication skills, with the ability to clearly explain technical concepts, modeling results, and data-driven insights to both technical and non-technical audiences.

Desired Qualifications:

• Experience building models with PyTorch, Keras, TensorFlow or similar deep learning libraries;
• Familiarity with large-scale geospatial data, especially weather data formats, APIs and storage;
• Knowledge and experience in the US energy industry;
• General understanding of battery energy storage and applications and applications to the US electricity grid.