Agentic RAG Systems & Multi-Agent Architectures: Developers Edition

4.8 (46)

·

7 Weeks

·

Cohort-based Course

Master Advanced Techniques for Building and Optimizing Agentic RAG Systems and Multi-Agent Workflows — Designed for Builders

Previously at

Google
Ucla
company logo
University of Minnesota

Course overview

The LLM Technical Course: Build and Deploy Production-Grade Gen AI Products

🧠 Masterclass in Agentic RAG & Agent Deployment:


Build Autonomous Systems with Routers, Agents, and Real-World LLMs

Welcome to the AI builder's dojo — a technically rigorous, unapologetically hands-on course for those who are done watching tutorials and ready to build autonomous, production-grade AI systems.


This isn't another passive online course. It's 15 live sessions7 deep-dive classes, 7 interactive office hours, and 1 epic Demo Day where you’ll present real builds.


We’ve stretched the course across 10 weeks so you can properly design, implement, and refine Agentic RAG systems with custom agents and routing logicnot just copy and paste pipelines.


🔧 What Makes This Course Different?


Other courses teach you what RAG is.

We go further — into Agentic RAG with intelligent routers, agent collaboration, and context-aware decision making.


Other courses demo CrewAI or AutoGen.

We teach you to build your own autonomous agents — and ship them to production.


Other courses use cosine similarity.

We’ll show you how to build retrieval systems that adapt, scale, and reason.


🧩 Who This Is For

If you’ve already built basic RAG apps, understand cosine similarity, vector databases, encoder-decoder models, and have some comfort with APIs and cloud infra — this is the advanced course you've been waiting for.


💥 What You Get


-10 weeks of live, high-signal content

-Weekly office hours for deep-dive help

-Real-world projects that you actually ship

-Guest lectures from AI industry leaders

-Early access to Traversaal.ai experimental tools

-Lifetime access to all materials & future updates


🚀 What You’ll Build and Learn


🧠 Agentic RAG: Beyond Just Retrieval

Design full-stack retrieval systems with autonomous agents, semantic chunking, and dynamic routers that reason about context and orchestrate multi-step tasks across tools and APIs.


🧭 Build Your Own Agent & Router Framework

No CrewAI, no wrappers. Build agents and decision routers from scratch. Understand how they communicate, choose tasks, and act — like actual autonomous systems.


📦 Hosting & Deploying LLMs

Deploy LLMs across cloud and serverless infrastructure, create inference endpoints, and understand how to monitor and scale them in real-world settings.


🔁 Continual Pretraining & Fine-Tuning

Avoid catastrophic forgetting while building pipelines for continual learning using causal language modeling and domain-specific corpora.


🧬 Model Merging & MoEs

Merge models with mergekit, use Mixture of Experts (MoE), and build adaptive routing strategies for better performance at scale.


🧮 Quantization & Inference Optimization

Speed things up and slim things down. Use quantization strategies that make your models faster and lighter without losing performance.


🛡️ Responsible AI Guardrails

Integrate ethics and safety using tools like NeMo, Colang, and Llama Guard to make sure your AI systems stay aligned and compliant.


🧠 Knowledge Graphs & DSPy

Structure your world with knowledge graphs and tap into DSPy to add logic and transparency to your AI’s decisions.


Throughout the course, we’ll reverse-engineer some of the most innovative AI systems out there — and give you exclusive access to early-stage tools being developed at Traversaal.ai, my AI startup.


📌 Prerequisites

Hands-on experience building RAG-based apps

Understanding of LLMs, encoders/decoders, and APIs

Some exposure to cloud platforms and basic DevOps


👉 Need a foundational course first? Try my other offering:

Building LLM Applications

✨ This Course Is For Builders

If you're looking for a shortcut, this isn’t it.

If you're ready to build autonomous AI systems that route intelligently, retrieve precisely, and reason like humans —


This course is for you if you are a:

01

Machine Learning Engineer exploring different techniques to scale LLM solutions

02

Researcher, who would like to delve in to various aspects of open-source LLMs

03

Software Engineer, looking to learn how to integrate AI into their products

What you’ll get out of this course

Advanced AI Architectures

Understand and implement complex AI architectures, including enterprise-level RAG systems and agentic RAG strategies. You will also dive deep into the Mixture of Experts (MoE) technique and other model merging strategies to enhance the capabilities of your AI systems.

Practical Skills for Deployment

From building semantic caches using GCP and Redis to deploying LLMs on serverless platforms like AWS Bedrock, you'll learn the practical skills to deploy and manage AI applications in real-world scenarios. 

Fine-Tuning Expertise

Acquire advanced techniques for fine-tuning LLMs, enabling you to adapt these models to specific tasks or domains and enhance their performance in targeted applications.

Efficient Inference Processing

Explore strategies for exploring and optimizing inference speeds, ensuring that your language models perform efficiently in real-time scenarios, a crucial skill for deploying responsive and scalable applications.

Knowledge of Responsible AI

Understand the importance of ethical AI development and learn to implement guardrails using tools like NeMo, Colang, and Llama Guard to ensure your AI systems align with responsible AI principles.




What’s included

Hamza Farooq

Live sessions

Learn directly from Hamza Farooq in a real-time, interactive format.

Lifetime access

Go back to course content and recordings whenever you need to.

Community of peers

Stay accountable and share insights with like-minded professionals.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

Maven Guarantee

This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.

Course syllabus

14 live sessions • 35 lessons • 6 projects

Week 1

Jul 12—Jul 13

    Recordings from previous Talks/ Sessions

    2 items

    Enterprise RAG Solutions with Semantic Caching

    6 items

    Jul

    12

    Session 1: Enterprise RAG

    Sat 7/124:00 PM—6:00 PM (UTC)

Week 2

Jul 14—Jul 20

    Optimizing and Deploying Large Language Models

    10 items

    Jul

    19

    Session 2: Deploying LLMs with Quantization

    Sat 7/194:00 PM—6:00 PM (UTC)

    Jul

    16

    Office Hours

    Wed 7/167:00 PM—7:30 PM (UTC)
    Optional

Week 3

Jul 21—Jul 27

    Jul

    26

    Session 3: Guardrails and AI Safety

    Sat 7/264:00 PM—6:00 PM (UTC)

    Module: DSPy and Implementing Guardrails for Responsible AI

    6 items

    Jul

    23

    Office Hours

    Wed 7/237:00 PM—7:30 PM (UTC)
    Optional

Week 4

Jul 28—Aug 3

    Holiday Assignment

    2 items

    Jul

    30

    Office Hours

    Wed 7/307:00 PM—7:30 PM (UTC)
    Optional

    Aug

    1

    Tech Friday: Deploying LLM Endpoints in Enterprise

    Fri 8/17:00 PM—8:00 PM (UTC)

Week 5

Aug 4—Aug 10

    Knowledge Graphs

    8 items

    Aug

    9

    Session 4: Knowledge Graphs

    Sat 8/94:00 PM—6:00 PM (UTC)

Week 6

Aug 11—Aug 17

    Autogen and Agents

    3 items

    Aug

    16

    Session 5: Agents

    Sat 8/164:00 PM—6:00 PM (UTC)

    Aug

    15

    Tech Friday: Agents in Action

    Fri 8/157:00 PM—8:00 PM (UTC)

    Aug

    13

    Office Hours

    Wed 8/136:00 PM—6:30 PM (UTC)

Week 7

Aug 18—Aug 24

    Semantic and Agentic RAG

    2 items

    Model Merging and Fine-tuning Video recordings

    2 items

    Aug

    20

    Office Hours

    Wed 8/206:00 PM—7:00 PM (UTC)

    Aug

    23

    Session 6: Agentic RAG and Semantic Chunking

    Sat 8/234:00 PM—6:00 PM (UTC)

Post-course

    Demo Day

    0 items

    Sep

    13

    Demo Day

    Sat 9/134:00 PM—6:00 PM (UTC)

4.8 (46 ratings)

What students are saying

Meet your instructor

Hamza Farooq

Hamza Farooq

I am the founder of Traversaal.ai, an LLM-based startup dedicated to creating scalable, customizable, and cost-efficient language model solutions for enterprises.


With over 15 years of experience in machine learning, my journey has spanned three continents and seven countries, covering a diverse range of industries such as tech, telecommunications, finance, and retail.


As a former Senior Research Manager at Google and Walmart Labs, I have led data science and machine learning teams, focusing on optimization, natural language processing, recommender systems, and time series forecasting.

I am also an adjunct professor at UCLA, and Instructor for Stanford Continuing Studies where I bridge the gap between academic theory and real-world AI applications.


Additionally, I frequently speak at conferences and conduct training sessions, sharing insights on large language models, deep learning, and cloud computing.

A pattern of wavy dots

Join an upcoming cohort

Agentic RAG Systems & Multi-Agent Architectures: Developers Edition

2025-cohort-3

$1,250

Dates

July 12—Aug 24, 2025

Payment Deadline

July 11, 2025
Get reimbursed

Course schedule

4-6 hours per week

  • Saturdays

    9:00 - 11:00am PT

    Virtual Class

  • Weekly projects

    2-3 hours per week

    Work in teams to build solutions, this requires engagement with other team members

Free resource

🚀 Join Me for a 7-Day Journey into AI Agents & LLM-Powered Applications

If you're curious about building the next generation of AI Agents and want to master how RAG systems, multi-agent frameworks, and LLMs are transforming the way we build, then this course is for you.


Over the next 7 days, I'll walk you through how developers, researchers, and teams are going beyond basic tools and building production-grade, low-latency, and secure AI solutions—and how you can do it too.

Get this free resource

Here's what others have to say about this course

Here's what others have to say about this course

Active hands-on learning

This course builds on live workshops and hands-on projects

Interactive and project-based

You’ll be interacting with other learners through breakout rooms and project teams

Learn with a cohort of peers

Join a community of like-minded people who want to learn and grow alongside you

Join the free course

Join here today

Frequently Asked Questions

A pattern of wavy dots

Join an upcoming cohort

Agentic RAG Systems & Multi-Agent Architectures: Developers Edition

2025-cohort-3

$1,250

Dates

July 12—Aug 24, 2025

Payment Deadline

July 11, 2025
Get reimbursed

$1,250

4.8 (46)

·

7 Weeks