GPU / AI

AI Systems Engineering

LLM serving, batching, KV cache, RAG, vector search, gateways, evals and observability.

4.8Focused trackIntermediate9 modules
Outcome

Learn the infrastructure concepts behind GPU, CUDA, AI serving and production backend systems.

Good for

Students moving toward GPU programming, AI infra, backend infra or systems design interviews.

Prerequisites

Comfortable C++ or Python basics, arrays, memory concepts and basic command-line workflow.

Curriculum

What you will study

Modules are shown like a course curriculum so you can scan the path before starting.

01LLM systems overview
02Tokenization
03Batching
04KV cache
05Embeddings
06Vector search
07RAG
08Model gateways
09Evals and observability