Skip to content

Courses

Curated courses for going deeper after this bootcamp. Each entry includes what's covered and who it's for.

Free courses

DeepLearning.AI Short Courses — deeplearning.ai/short-courses A collection of 1–3 hour courses, most co-created with the relevant company: - Building Systems with ChatGPT — prompt chaining, moderation, evaluation (with OpenAI) - LangChain for LLM Application Development — LCEL, agents, memory (with LangChain) - Building and Evaluating Advanced RAG — query translation, reranking, RAGAS (with LlamaIndex) - Fine-tuning Large Language Models — instruction tuning, PEFT overview (with Lamini) - LangGraph Multi-Agent Workflows — StateGraph, supervisor patterns (with LangChain) - AI Agents in LangGraph — tool use, memory, human-in-the-loop (with LangChain)

Who it's for: Everyone. These are the best free resources for practical LLM engineering.

fast.ai Practical Deep Learning — fast.ai Bottom-up approach: build systems first, understand theory after. - Part 1: Image/tabular ML, transfer learning - Part 2: Stable diffusion, NLP transformers, building from scratch

Who it's for: Those who want to understand how transformers work at the implementation level.

Hugging Face NLP Course — huggingface.co/learn End-to-end NLP with Transformers: tokenizers, fine-tuning, pipelines, deployment. Who it's for: Anyone working with local models and the HuggingFace ecosystem.

LLM Engineering: Master AI, Large Language Models — Udemy (Ed Donner) Practical LLM engineering: frontier models, RAG, fine-tuning, agents, deployment. Who it's for: Those who want a structured path similar to this bootcamp with additional depth.

Books

Building LLMs for Production (Bouchard & Peters, 2024) Covers RAG, agents, evaluation, and deployment with production-focused patterns.

Designing Machine Learning Systems (Huyen, 2022) Not LLM-specific, but the data, monitoring, and deployment chapters apply directly to LLM systems.

Documentation (the best reference)