Internship Machine Learning for Predictive Reliability Analytics - Heat Pumps

We are looking for a motivated intern to help us continue developing our machine-learning solutions for heat pump reliability. You will build on what we've already started, work on improving our current models, and explore how we can apply these ideas to additional reliability use cases. Most of your work will be done in Databricks.
During your internship, you will contribute to the review and enhancement of existing data preparation and feature engineering approaches.
You will support the optimization and evaluation of existing machine learning models.
In addition, you will investigate potential new features and early risk indicators within field and IoT data.
You will also develop reproducible ML workflows in Databricks using MLflow.
Furthermore, you will adapt and assess existing approaches for additional product issues and reliability-related use cases.
Moreover, you will explore the application of Generative AI to transform model outputs and key risk drivers into concise and understandable reports for engineers.
Finally, you will communicate findings through data visualizations, short presentations, and technical documentation.
Education: Master studies in the field of Data Science, Artificial Intelligence, Computer Science, Information Systems, Engineering or a comparable quantitative or technical field
Experience and Knowledge: practical knowledge of machine learning, model evaluation, feature engineering, and data preprocessing; good Python skills; experience with Databricks, MLflow, PySpark or Generative AI applications is a plus
Personality and Working Practice: you excel at driving tasks forward independently, organizing your workflows systematically, while communicating technical results with high clarity
Work Routine: we offer you the opportunity to work in a hybrid setup with regular presence in Wernau
Enthusiasm: interested in applying machine learning to real-world products and IoT data
Languages: very good in English

Employment type
Full-time

Work arrangement
Hybrid