AI Engineering

Module 1 · 0/4 done · 72 min

Foundations of AI & LLMs

What AI, machine learning and large language models actually are, how an LLM turns text into predictions, what it can and cannot do, and the landscape an AI engineer works in.

Module 2 · 0/4 done · 72 min

Prompt Engineering

The craft of instructing LLMs reliably: the anatomy of a prompt, system vs user roles, few-shot examples, chain-of-thought reasoning, and getting consistent structured output.

Module 3 · 0/4 done · 70 min

Calling AI APIs

How to actually talk to an LLM in code: API keys and security, the request/response shape, controlling output with parameters, streaming, and handling tokens, cost and errors in production.

Module 4 · 0/4 done · 72 min

RAG & Embeddings

Grounding LLMs in your own data: what embeddings are, how vector search finds relevant text, how to chunk documents well, and how to build a retrieval-augmented generation (RAG) pipeline that answers from real sources.

Module 5 · 0/4 done · 70 min

Building AI-Powered Apps

Turning model calls into real products: app architecture, managing conversation memory and context, designing good AI user experiences, and adding guardrails so the product behaves safely and predictably.

Module 6 · 0/4 done · 71 min

Agents & Tools

Giving models the ability to act: tool and function calling, letting an LLM use external capabilities, building multi-step agents that plan and execute, and orchestrating reliable agentic workflows.

Module 7 · 0/4 done · 71 min

Evaluation, Cost & Safety

Making AI features trustworthy and affordable: how to evaluate output quality, detect and reduce hallucination, defend against prompt injection and misuse, control cost, and build AI responsibly.

Module 8 · 0/4 done · 68 min

Deployment & Career

Shipping and sustaining AI products, and building a career: deploying AI features, monitoring and improving them in production, keeping up in a fast-moving field, and building a portfolio that lands AI-engineering work.