CIS 6930 Spring 26
Data Engineering at the University of Florida
Course Schedule - Spring 2026
Key Dates
- Classes Begin: January 12, 2026
- MLK Day (no class): January 19, 2026
- Spring Break: March 14-21, 2026
- Classes End: April 22, 2026
- Finals: April 25 - May 1, 2026
Assignments
| Assignment | Due Date | Points | Description |
|---|---|---|---|
| HiPerGator Training | Jan 23, 8:30 AM | 5 | Complete UF RC training |
| Assignment 0 | Jan 28, 11:59 PM | 50 | Python, GitHub, LLM basics |
| Assignment 1.5 | Feb 11, In-Class | 12 | MCP on HiPerGator (in-class) |
| Assignment 1 | Feb 18, 11:59 PM | 100 | MCP data pipeline |
| Quiz: ML Fundamentals | Feb 18, 8:30 AM | 10 | sklearn API, metrics |
| Assignment 2 | Mar 9, 11:59 PM | 60 | RAG system implementation |
Project Milestones
Repository: cis6930sp26-project (individual)
| Milestone | Due Date | Points | Description |
|---|---|---|---|
| Project Proposal | Feb 25, 11:59 PM | 100 | Research question + initial design |
| Code Checkpoint | Mar 23, 11:59 PM | 150 | Working prototype |
| Draft Paper | Mar 30, 11:59 PM | 100 | Complete draft |
| Final Paper | Apr 13, 11:59 PM | 400 | Full evaluation |
| Presentation | Week of Apr 20 | 150 | 10-min presentation |
More assignments will be released as the semester progresses.
Weekly Schedule
Week 1: Course Introduction (Jan 12, 14, 16)
| Day | Topic | Activity |
|---|---|---|
| Mon | Course Introduction | Syllabus, expectations |
| Wed | Git/GitHub Crash Course | Live demo |
| Fri | Topics Overview | Data engineering + LLMs |
Assigned: Assignment 0
Week 2: MCP & Data Extraction (Jan 21, 23)
Monday Jan 19 - MLK Day, no class
| Day | Topic | Activity |
|---|---|---|
| Wed | MCP Fundamentals | Architecture, primitives |
| Fri | HiPerGator Setup | Matt Gitzendanner guest talk |
Due: Assignment 0 (Jan 28), HiPerGator Training (Jan 23)
Assigned: Assignment 0.5 (Skipped)
Readings: MCP Specification, MCP Quickstart Guide (see lecture readings)
Week 3: Prompt Engineering (Jan 27, 29, 31)
| Day | Topic | Activity |
|---|---|---|
| Mon | Prompting Fundamentals | Zero-shot, few-shot, prompt structure |
| Wed | Chain-of-Thought | CoT theory, Zero-shot CoT, Tree/Graph of Thoughts |
| Fri | Reading Papers + Structured Outputs | 3-pass method, JSON mode |
Due: Assignment 0 (Jan 28) Assigned: Assignment 1, Assignment 2
Readings: Chain-of-Thought Prompting, How to Read a Paper (see lecture readings)
Tools: Navigator CLI - Command-line tool for querying NavigatorAI
Week 4: Data Integration (Feb 2, 4, 6)
| Day | Topic | Activity |
|---|---|---|
| Mon | Prompt Engineering Lab | Structured outputs |
| Wed | Data Integration | Schema mapping |
| Fri | Entity Resolution | Traditional methods |
Assigned: Assignment 1 (due Feb 18)
Readings: LinkTransformer (Arora & Dell, ACL 2024) (see lecture readings)
Week 5: Data at Scale & Guest Speakers (Feb 9, 11, 13)
| Day | Topic | Activity |
|---|---|---|
| Mon | Guest Speaker: Dr. Shiree Hughes | Big Data at General Motors |
| Wed | Assignment 1.5: MCP on HiPerGator | In-class hands-on activity |
| Fri | Guest Speaker: Mikhail Sinanan | Data Engineering at Spotify |
Due: Assignment 1.5 (Feb 11, In-Class)
Readings: Apache Kafka, Spark, Hadoop introductions; Spotify Data Platform (see lecture readings)
Lecture: Slides from Dr. Hughes are available here.
Week 6: ML Fundamentals (Feb 16, 18, 20)
| Day | Topic | Activity |
|---|---|---|
| Mon | ML Fundamentals | Classification, regression, clustering; sklearn API |
| Wed | Evaluation Metrics | ROC/AUC, cross-validation, hyperparameter tuning |
| Fri | Project Proposal Workshop | Example proposals, research question refinement |
Due: Assignment 1 (Feb 18), Quiz: ML Fundamentals (Feb 18, 8:30 AM), Peer Reviews (Feb 21) Assigned: Project Proposal (due Feb 25)
Friday Workshop:
- Example proposals for Directions A, B, and C
- Common pitfalls to avoid
- Partner activity: refine your research question
- Class discussion: volunteer proposals
Topics Covered:
- Classification vs Regression vs Clustering
- Train/Validation/Test splits, cross-validation
- sklearn API: fit(), transform(), fit_transform(), Pipeline
- Precision, Recall, F1, Confusion Matrix
Week 7: RAG Systems (Feb 23, 25, 27)
| Day | Topic | Activity |
|---|---|---|
| Mon | RAG Architecture | Components, retrieval methods, augmentation strategies |
| Wed | Vector Databases | Chroma, FAISS hands-on demo |
| Fri | Chunking Strategies | Discussion |
Due: Project Proposal (Feb 25) Assigned: Assignment 2 (RAG System, 60 pts, due Mar 9)
Readings: Lewis et al. (2020) RAG paper, COLING 2025 RAG Best Practices (see lecture readings)
Supplementary: Embeddings Primer - Background on text embeddings for students who need a refresher
Week 8: LLM Evaluation (Mar 2, 4, 6)
| Day | Topic | Activity |
|---|---|---|
| Mon | LLM Evaluation Fundamentals | Metrics, benchmarks, and non-determinism |
| Wed | Building Benchmarks | RAGAS + evaluation demo |
| Fri | Project Workshop | Pitch circle, pair debugging, office hours |
Upcoming: Assignment 2 (Mar 9, 11:59 PM)
Readings: RAGAS (EACL 2024), In Benchmarks We Trust… Or Not? (see lecture readings)
Week 9: Project Work (Mar 9, 11, 13)
| Day | Topic | Activity |
|---|---|---|
| Mon | RAGAS Demo + Q&A | Assignment 2 support |
| Wed | Project Work Session | Code checkpoint preparation |
| Fri | Project Work Session | Individual consultations |
Due: Assignment 2 (Mar 9, 11:59 PM) Upcoming: Code Checkpoint (Mar 23)
⏸️ Spring Break (March 14-21)
No classes. Enjoy your break!
Return: Monday, March 23
Week 10: Ethics & Human-AI (Mar 23, 25, 27)
| Day | Topic | Activity |
|---|---|---|
| Mon | AI Fairness & Bias | Bias in data systems |
| Wed | Human-in-the-Loop Systems | Agent design patterns |
| Fri | Work Session | Code checkpoint feedback |
Due: Code Checkpoint (Mar 23, 11:59 PM)
Readings: Bias and Fairness in LLMs Survey, Building Effective Agents (see lecture readings)
Week 11: Paper Writing Sprint (Mar 30, Apr 1, 3)
| Day | Topic | Activity |
|---|---|---|
| Mon | Paper Writing Workshop | Structure, style, clarity |
| Wed | Work Session | Paper writing |
| Fri | Work Session | Paper drafting |
Due: Draft Paper (Mar 30, 11:59 PM)
Readings: How to Write a Great Research Paper (see lecture readings)
Week 12: Crowdsourcing (Apr 6, 8, 10)
| Day | Topic | Activity |
|---|---|---|
| Mon | Crowdsourcing & Annotation | Platforms, quality control |
| Wed | Annotation Design | Guidelines, interfaces |
| Fri | Work Session | Paper revisions |
Readings: HumEval Workshop, Capturing Perspectives of Annotators (see lecture readings)
Week 13: Peer Review (Apr 13, 15, 17)
| Day | Topic | Activity |
|---|---|---|
| Mon | Writing Good Reviews | Conference standards |
| Wed | Work Session | Paper finalization |
| Fri | Work Session | Peer reviews |
Due: Final Paper (Apr 13, 11:59 PM)
Readings: ACL Reviewer Guidelines (see lecture readings)
Week 14: Presentations (Apr 20, 22)
| Day | Topic | Activity |
|---|---|---|
| Mon | Course Wrap-up | Lessons learned |
| Wed | Presentations | Final presentations |
Due: Presentation (Week of Apr 20)
Week 15: Finals (Apr 25 - May 1)
- Final presentation viewing
- Peer presentation ratings
- Course evaluations