Unlocks after Module 5The AI Engineering Program

Module 6: LLM Application Engineering

Build and ship an LLM-powered service that returns reliable, structured results, with cost and latency under control.

30guided hours

12lessons

6 of 13in the program

Lessons

12 lessons, in order. Each one unlocks when you finish the one before it.

6.1
How LLMs are served: tokens, context windows, sampling, cost and latency maths
6.2
One client for many models: free-tier APIs and local models
6.3
Prompts that hold up: instructions, examples, delimiters and prompt versioning
6.4
Structured outputs: JSON schemas, Pydantic validation and retries
6.5
Function calling and tool use
6.6
Context engineering: deciding what goes into the window
6.7
Multimodal inputs: images, PDFs and speech
6.8
Streaming, caching, rate limits and fallbacks
6.9
Serving an AI feature with FastAPI
6.10
Front ends for AI apps: Streamlit, then a first look at TypeScript and Next.js
6.11
Privacy and responsible AI, including India's DPDP Act 2023
6.12
Module project

AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.