IMEN891KData Engineering

POSTECH

IMEN891K / IDSC501 / AXGS-501Fall 2026

Data Engineering

This course covers the data side of AI systems: everything that happens before and after the model. We collect and prepare data, store and process it at scale, and then run models and agents on it. In a team project, students build a product on a real data pipeline from end to end.

Instructor
Sangwoo Mo Prof. Sangwoo MoPOSTECH IME
Location & Time

Science Building 4, Room 302

Tuesdays & Thursdays 9:30 – 10:45 KST

Office Hours
Tuesdays 11:00 – 12:00, Room 319
Other Terms
Fall 2025
Other Courses
Programming for AX

Course Outline

  1. Part ILectures 2 – 5 Collection and Preparation Collect data, explore it, and clean, integrate, transform and reduce it.
  2. Part IILectures 6 – 13 Storage Store and query it with SQL and NoSQL, then process it at scale in batches, warehouses and streams.
  3. Part IIILectures 14 – 17 Monitoring and Updates Run models and agents on the data: ML systems, LLM systems, RAG and agents.

Grading

  • Midterm Exam40%
  • Project Proposal20%
  • Project Final40%

Attendance is not graded, but missing more than 1/3 of the classes results in an F.

Resources

Reference Courses

Past Exams