CS 452 - Data Engineering with AI

Unit(s): 4

In this 15-week project-based course, students will build a complete, AI-augmented data platform from scratch entirely within a local environment. Starting with a rapid setup, they will tackle a new part of the pipeline every week, moving from raw data ingestion to intelligent, automated analytics. They will construct a scalable data lakehouse using industry-standard open-source tools like Apache Spark, Airflow, dbt, and Iceberg. Then, they will supercharge their system with AI, using LangChain to build smart data-cleaning agents and LLMs to generate code. They will prove their skills with a mid-term sprint before teaming up to build a final, portfolio-ready project–a sophisticated system with real-time capabilities that they will demo and document.

Prerequisite: CS 362 with a minimum grade of C
College of Arts & Sciences