The
Multiverse
School

2-Week Course

Advanced Retrieval Augmented Generation

04.28.25 - 05.07.25 2 weeks live & online, 6 hours in class

Master cutting-edge RAG techniques to build high-performance AI systems with precision retrieval and contextual understanding.

with Liz Howard

Tell me when the next one is scheduled

This run has finished. Leave your email and we will tell you when the next one opens.

We'll email you to confirm, then when the next one is scheduled, plus up to two reminders. Unsubscribe any time.

What You'll Learn

Take your RAG systems to the next level with advanced embedding techniques, vector databases, and neural re-ranking. This comprehensive course covers the full spectrum of modern retrieval methods that power today's most capable AI systems.

Deep dive into embedding models (BERT, Sentence-Transformers), efficient vector search algorithms (FAISS, HNSW), vector database performance optimization, neural re-rankers, and techniques for training custom embedding models tailored to your specific domain.

Course Schedule

2Weeks
6Classroom Hours
Week 1

Embedding Models

Monday, April 28 at 5:00 PM - 6:30 PM PDT

Deep dive into embedding models including BERT and Sentence-Transformers. Learn how these models encode semantic meaning and how to select the right embedding model for your specific use case.

1.5h
Week 1

Vector Search Algorithms

Wednesday, April 30 at 5:00 PM - 6:30 PM PDT

Explore FAISS and Hierarchical Navigable Small Worlds (HNSW) algorithms. Understand the tradeoffs between search speed, memory usage, and retrieval accuracy in these advanced vector search techniques.

1.5h
Week 2

Vector Database Performance

Monday, May 05 at 5:00 PM - 6:30 PM PDT

Compare different vector stores and their performance characteristics. Learn how to optimize your vector database for your specific retrieval needs and scale requirements.

1.5h
Week 2

Neural Re-ranking & Custom Embeddings

Wednesday, May 07 at 5:00 PM - 6:30 PM PDT

Master neural re-ranking techniques to dramatically improve retrieval precision. Learn how to train custom embedding models on your domain-specific data for optimal performance.

1.5h

All times shown in Pacific Time

Who Is This Course For

Software engineers, data scientists, and AI practitioners looking to implement advanced retrieval systems for LLMs

Who this is for & what you'll need

Solo coding

You should be able to write in some language on your own.

Strong computer or subscription

Use your own capable machine, or a paid hosted option below.

On your own machine

Local FAISS/HNSW vector search and fine-tuning custom embedding models (heavier compute).

Or use the hosted option

Or a hosted vector DB, Pinecone / Weaviate free tiers; OpenAI API key.

Where This Class Leads

What you leave able to do

  • transform a corpus into an embedded index
  • justify a vector index for a latency and corpus budget
  • justify an embedding model and its dimensionality
  • measure whether a fine tune changed behaviour
  • construct a retrieval system
  • design a chunking strategy against measured retrieval
  • reconcile a failing retrieval by reranking and rewriting

How you show it. A set of questions the first-pass retriever answered wrongly, the reranked or rewritten run, and the before-and-after scores on the same set.

It sits on one path

The AI Builder9 of 12 after RAG & Memory · before Production Agent Engineering

About 11 hours of practice sit behind this one. See what your hours buy.

Join the Course

Pay what you can - accessible learning for all

The minimum is $100, it keeps out spam. Need a larger discount? Apply for a scholarship. We offer 100% scholarships, no one is turned away for lack of funds.

Suggested $200 pay what you can

Suggested price • Pay what you can

  • Deep dive into advanced RAG techniques
  • Four 90-minute live sessions
  • Hands-on experience with embedding models
  • Learn vector search algorithms and database optimization
  • Master neural re-ranking techniques
  • Please self-select into this tier- if you need it, use it
Pay What You Can

Secure payment via Stripe

Suggested $300 pay what you can

Suggested price • Pay what you can

  • Deep dive into advanced RAG techniques
  • Four 90-minute live sessions
  • Hands-on experience with embedding models
  • Learn vector search algorithms and database optimization
  • Master neural re-ranking techniques
  • Help pay for underrepresented folks in tech!
Pay What You Can

Secure payment via Stripe

Instructor

Liz Howard

Liz Howard

Future Infinitive☸️ (Liz Howard) Founder & Professor, The Multiverse School Computer Science · AI · Cybersecurity Formerly faculty, Cal State Monterey Bay Co-founder, Hipcamp Previously built Hackbright Academy, Girl Develop It, Galvanize, Enki

GitHub LinkedIn Website

Frequently Asked Questions

How are classes delivered?

All classes are live and online via video call. Sessions are recorded so you can review them later if you miss one.

What does "pay what you can" mean?

We show a suggested price, but you can pay any amount. If you need a larger discount, apply for a scholarship, we offer 100% scholarships and no one is turned away for lack of funds.

Do I need prior experience?

Solo coding. You should be able to write in some language on your own.

What do I get when I enroll?

Live sessions with the instructor, access to course curriculum materials, community access via our Matrix chat server, and recordings of all sessions.

Want to schedule this course for your team?

Contact us: [email protected]