AI Engineering

Learn LLM foundations and AI application development — 32 topics across 9 chapters covering transformers, prompts, RAG architectures, agent systems, and deployment patterns.

Start Learning View Modules

32

Topics

9

Chapters

30h

Est. Time

Progress0/32 (0%)

All Modules

Click any topic to start learning

1

LLM Foundations

6 topics

0% done

1What is AI, LLM, and Transformers?2The LLM Lifecycle: Base vs Instruct Models 3How Transformer Models Work & KV Cache 4Tokenization & Embeddings 5Fine-tuning vs. RAG 6The 3 Layers of AI: From Chatbots to Agents

2

Advanced Prompt Engineering

3 topics

0% done

1Zero-shot and Few-shot Learning 2Chain-of-Thought (CoT)3ReAct Pattern

3

RAG & Vector Databases

3 topics

0% done

1Vector Databases (Pinecone, Milvus)2Semantic Search & Chunking 3Evaluating RAG Performance

4

Building AI Agents

5 topics

0% done

1Tool Use (Function Calling)2MCP (Model Context Protocol)3Multi-Agent Architectures 4LangGraph & State Machines 5A2A (Agent-to-Agent Protocol)

5

AI Engineering Stack

3 topics

0% done

1Streaming & Vercel AI SDK 2Observability & Tracing 3Caching & Cost Optimization

6

Advanced RAG Engineering

3 topics

0% done

1Why Naive RAG Fails in Production 2GraphRAG & Knowledge Graphs 3RAG Evaluation & Observability

7

LLM Inference Engineering

3 topics

0% done

1vLLM & PagedAttention 2Quantization: GGUF, AWQ & EXL2 3Prompt Caching & Speculative Decoding

8

Fine-Tuning & Model Alignment

3 topics

0% done

1QLoRA & Parameter-Efficient Fine-Tuning 2DPO & RLHF: Aligning LLMs to Human Preferences 3Synthetic Data Generation at Scale

9

Context & Memory Management

3 topics

0% done

1Context Window Physics & The "Lost in the Middle"2Agentic Memory Architecture 3Context Distillation & KV Compression