⚙️ AI Engineering Week 1 of 14 BSc · Y1 ⏱ ~50 min

Week 1: The AI Engineering Landscape & Model Lifecycle

Understand the AI engineering paradigm: model lifecycle management, deployment pipelines, the engineering toolchain, and what sets AI engineering apart.

University of America

AIE101 — Lecture 1 · BSc Y1

🎬 CC Licensed Lecture

0:00 / —:—— 📺 MIT OpenCourseWare (CC BY-NC-SA)

🎯 Learning Objectives

Distinguish AI research from AI engineering roles and responsibilities
Map the full ML model lifecycle from data to production
Set up a professional AI engineering development environment
Evaluate and choose the right framework for a given AI problem

Topics Covered This Lecture

AI Engineering vs AI Research

The ML Model Lifecycle

Development Environment & Toolchain

Frameworks: PyTorch, TensorFlow, JAX

📖 Lecture Overview

This first lecture establishes the foundational framework for Foundations of AI Engineering. By the end of this session, you will have the conceptual grounding and practical starting point needed for the rest of the course.

        Why this matters
        Understand the AI engineering paradigm: model lifecycle management, deployment pipelines, the engineering toolchain, and what sets AI engineering apart. This lecture sets up everything that follows — make sure you understand the core concepts before proceeding to Week 2.
      

Key Concepts

The lecture introduces the four main pillars of this course: AI Engineering vs AI Research, The ML Model Lifecycle, Development Environment & Toolchain, Frameworks: PyTorch, TensorFlow, JAX. Each will be explored in depth over the 14-week curriculum, with hands-on projects reinforcing theory at every stage.

# Quick Start: verify your environment is ready for AIE101
import sys
print(f"Python {sys.version}")

# Check key libraries are installed
try:
    import numpy, pandas, matplotlib
    print("✅ Core libraries ready")
except ImportError as e:
    print(f"❌ Missing: {e} — run: pip install numpy pandas matplotlib")

This Week's Focus

Focus on mastering: AI Engineering vs AI Research and The ML Model Lifecycle. These are the prerequisites for everything in Week 2. The concepts build on each other — do not skip the practice exercises.

📋 Project 1 of 3 50% of Final Grade

AIE101 Project 1: AI System Audit

Choose a production AI system (e.g., a recommendation engine, spam filter, or image moderation system) and perform a complete audit: architecture, data pipeline, deployment, monitoring, and failure modes.

System architecture diagram
Data flow and pipeline documentation
Deployment and monitoring strategy review
Risk assessment and failure mode analysis

50%

3 Projects

20%

Midterm Exam

30%

Final Exam

📝 Sample Exam Questions

These represent the style and difficulty of questions you'll see on the midterm and final. Start thinking about them now.

Conceptual Short Answer

What are the key differences between a research ML model and a production AI engineering system?

Analysis Short Answer

Describe the 5 stages of the ML model lifecycle. What engineering challenges arise at each stage?

Applied Code / Proof

What is model drift and how does it affect production AI systems over time?