You explore core machine learning concepts by building regression models in Jupyter notebooks, using techniques like linear regression, random forests, and XGBoost. You implement classification workflows, refactor them into reusable Python functions, and track experiments with MLflow. A production-grade ML pipeline is orchestrated with Dagster, using LakeFS for data versioning and triggering automated runs on data changes. The pipeline is polished into a clean, reproducible project, with a final product prepared for clear and confident presentation.