Track 6 of 6

AI System Design

Case studies that combine what the earlier tracks teach into whole systems under real limits on latency, cost, and quality.

You design production AI systems or are preparing for system design interviews.

Case study · 6 steps

Serve an LLM

Plan GPUs, latency, and cost for a 7B chat model from first principles

Builds on KV Cache, Quantization, Continuous Batching, Decoder-Only Transformers Case study · 6 steps

Build a RAG System

Size chunking, the vector index, search, reranking, and generation for a RAG system

Builds on Retrieval-Augmented Generation, Embeddings, Chunking & Reranking for RAG, Vector Search & HNSW, K-Means Clustering, KV Cache Case study · 6 steps

Design a Recommendation Feed

Retrieval, ranking, re-ranking, feedback loops and A/B test length for a 1M-item feed

Builds on Embeddings, Vector Search & HNSW, K-Nearest Neighbors, Gradient Boosting, Model Evaluation & Metrics, Class Imbalance & Resampling, Hypothesis Testing

Next case studies: building a RAG system and designing a recommendation feed. Case studies build on AI Engineering, so that track is a good place to start.