ed-donner/llm_engineering

Repo to accompany my mastering LLM engineering course

What it solves

This project is a complete curriculum for learning large language model (LLM) engineering from the ground up. It removes the guesswork by offering a structured 8-week path with hands-on projects that progressively build expertise. It also addresses practical concerns like setup difficulties, API costs, and choosing between paid and free models.

How it works

The course is organized into weekly folders, each representing a module with labs and code. It starts with an instant gratification exercise using Ollama to run local models like Llama 3.2, so learners see results immediately. Then it moves to full environment setup with tools like Cursor (AI coding) and Google Colab for GPU access. Learners use OpenAI and Anthropic APIs, with guidance to keep costs minimal. The final week ties everything together by building a powerful autonomous agentic AI solution.

Who it’s for

This is for anyone wanting to learn LLM engineering, whether you have programming experience or are starting fresh. The README answers common questions about prerequisites, job prospects, and using free or alternative models. The course emphasizes a 'doing' approach, encouraging learners to run code, experiment, and tweak projects.

Highlights

  • 8-week structured curriculum with progressive, cumulative projects
  • Immediate hands-on results with Ollama and local models like Llama 3.2
  • Detailed setup instructions for all platforms and free alternatives to paid APIs
  • Cost management tips, keeping total course spend to a few dollars
  • Final week builds an autonomous agentic AI solution
  • Community support via email, LinkedIn, YouTube, and a digital twin for FAQs

Related

  • Project
    Azure-Samples/azure-search-openai-demo

    A reference RAG chat application that allows users to interact with their own documents using Azure OpenAI and Azure AI Search.

  • Project
    lingfengQAQ/webnovel-writer

    Webnovel Writer is a Claude Code plugin that lets authors write long‑form web novels with AI while preserving plot consistency. It offers slash‑commands for initializing a book, planning outlines, writing and reviewing chapters, querying stored facts, and viewing a read‑only dashboard. Facts are recorded in a “Story System”, indexed with RAG (or BM25 fallback), and projected into summaries and long‑term memory so the model remembers characters, foreshadowing, and world rules across hundreds of chapters.

  • Project
    stanfordnlp/stanza

    A Python NLP library from Stanford that provides accurate neural processing tools for 60+ languages and a wrapper for the Java Stanford CoreNLP software.

  • Project
    NirDiamant/Prompt_Engineering

    A GitHub repository with 22 interactive tutorials teaching prompt engineering — from basic prompt writing to advanced techniques like chain-of-thought and prompt security — aimed at both beginners and experienced AI practitioners.