Improving RAG: Embedding models & representation learning

Lightning Lessons

Practical skills & tools to accelerate your career

Improving RAG: Embedding models & representation learning

Hosted by Jason Liu and Daniel Svonava

Tue, Sep 23, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

By continuing, you agree to Maven's Terms and Privacy Policy.

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

Tue, Sep 23, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

What you'll learn

Building Effective Embedding Pipelines

Students will learn to build embedding systems integrating databases, rerankers, and query models at scale.

Strategic Model Selection & Training Decisions

Students will learn frameworks for choosing pre-trained models, when to fine-tune, and evaluating training approaches.

Production AI Search Implementation

Students will gain insights from real-world case studies of deploying embedding systems in e-commerce and enterprise.

Why this topic matters

Embedding models power modern AI search, recommendations, and matching systems that billions of users interact with daily. As semantic understanding becomes essential for connecting users to relevant content, mastering embedding pipelines is crucial for AI practitioners. This knowledge bridges theory and practice, helping you avoid costly pitfalls and build production systems that scale.

You'll learn from

Jason Liu

Consultant at the intersection of Information Retrieval and AI

Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.

Daniel Svonava

CEO at Superlinked

Daniel is the CEO & co-founder of Superlinked.com, an open source framework and ML infrastructure platform for building intelligent search, personalization and analytics experiences with vector embeddings that combine structured and unstructured data. Previously, Daniel was an ML Tech Lead at YouTube, where he built ads forecasting infrastructure that powered the buying flows of $10B/y-worth of ads.

worked with