- Hugging Face
- Free
- Intermediate
The LLM Course
Deep, hands-on foundation for open models: transformers, the Hub, fine-tuning and reasoning models.
Open course : The LLM Course. Opens the provider site in a new tab
Engineers / Intermediate
LLM apps and RAG
Build an application on a language model: open-model foundations, retrieval, the Claude API and a test set that tells you if it works.
Who it is for
Engineers who want to ship a retrieval-based assistant, from first prototype to measured quality.
- Steps
- 8
- Level
- Intermediate
What you can do afterwards
- Build a retrieval pipeline with citations
- Measure answer quality on your own questions
- Choose between an API and a self-hosted model
- Sit the Generative AI Engineer Associate exam
Start here
Take the NexOps course
AI agents in production. Tools, memory, evaluation, guardrails, cost and operations, with the model of your choice
This path begins with our own course, with lessons, knowledge checks and labs. The external courses below are extra practice.
Extra practice
Course
Course
- DeepLearning.AI
- Cost not stated
- Intermediate
- 26 h 3 min
Retrieval Augmented Generation (RAG)
A broad RAG course covering the whole pipeline from retrieval to generation.
Open course : Retrieval Augmented Generation (RAG). Opens the provider site in a new tab
Course
- DeepLearning.AI
- Cost not stated
- Intermediate
- 1 h 2 min
Advanced Retrieval for AI with Chroma
A short follow-up on better retrieval quality: query rewriting and reranking.
Open course : Advanced Retrieval for AI with Chroma. Opens the provider site in a new tab
Course
- Anthropic
- Free with an account
- Intermediate
Building with the Claude API
The official Claude API course: tool use, prompt caching, extended thinking and citations.
Open course : Building with the Claude API. Opens the provider site in a new tab
Build
A RAG assistant with a test set
Goal. Answer questions about a document set, with citations, and prove the quality on twenty questions you wrote first.
What to do
- Choose 30 to 50 documents and write 20 questions with the answer you expect for each.
- Chunk, embed and index the documents. Return the three best chunks for a question.
- Generate the answer from those chunks only, and cite the chunk.
- Run the 20 questions after every change and keep a score per run.
What good looks like. You can say which change raised or lowered the score, and the assistant says when it does not know.
Read
Posts to read
What drives cost and latency once the assistant has users, and why routing is a quality question.
Check
API or self-hosted model
Answer a few questions about your data and constraints and see which option fits.
Certify
- Databricks
- Paid exam
- Intermediate
- 1 h 30 min
Databricks Certified Generative AI Engineer Associate
The credential for RAG and agent applications on Databricks, from design to evaluation.
Course details come from each provider. Check the provider page for the latest.
Next path
- Engineers
- Advanced
AI agents, MCP and evaluation
Agents with tools, the Model Context Protocol and the part most teams skip: an evaluation set and guardrails before production.
View the pathLearn this with your team
We run workshops for company teams and for students, tailored to your stack.
Learn this with your team
Next step
Want your team to learn this together?
We give workshops to company teams and students, on-site or online. Tell us who the participants are and what they should be able to do afterwards.
Accepting projects for Q4 2026