Generative AI Engineering: LLMs, RAG, and Agentic Systems

Learn to design and implement GenAI workflows, multi-agent systems, LangChain, LangGraph, MCP, and model fine-tuning

  • 0.0 (0 Reviews)
  • 0 Students
  • 269 Lessons
  • Rajeev Sakhuja

Course Overview

Build Real-World Generative AI Systems with LLMs, RAG, and AI Agents

Go beyond prompts and chatbots. This course takes you on a complete, progressive journey from Generative AI fundamentals to advanced system-level techniques.

You’ll start by mastering the core concepts of LLMs, NLP, and AI model behavior, then move into applying RAG pipelines, vector search, and prompting patterns. Finally, you’ll tackle advanced topics such as agentic systems, multi-agent orchestration, LangGraph workflows, MCP, and model fine-tuning.

Learn to design and implement intelligent AI workflows and system components using multiple LLMs, LangChain, LangGraph, embeddings, and agentic reasoning—without the pressure of building full production applications.

Skip the beginner fluff—this is for engineers, architects, and technical founders who want to understand how modern GenAI systems are actually structured and engineered.


What You Will Learn

  1. Understand Generative AI foundations and how LLMs work, including OpenAI, Claude, Gemini, and Hugging Face models.

  2. Apply RAG pipelines, vector search, embeddings, and structured outputs to create robust AI workflows.

  3. Learn prompting techniques, in-context learning, and fine-tuning strategies for advanced LLM behavior.

  4. Build and test agentic and multi-agent systems using LangChain and LangGraph.

  5. Explore MCP servers and clients to integrate LLM reasoning with external tools and services.

  6. Understand system-level best practices for efficiency, scalability, cost, and responsible AI deployment.


Hands-On Learning

This is a learning-by-doing course, focused on frameworks, patterns, and exercises, rather than fully functional apps. You will:

  • Work with multiple LLMs and open-source models to understand their behavior.

  • Implement retrieval pipelines, multi-agent patterns, and workflows in hands-on exercises.

  • Explore LangChain, LangGraph, embeddings, vector databases, and MCP integration in manageable components.

  • Gain practical, reusable code snippets and exercises without the stress of shipping a full product.


Who This Course Is For

  • Software engineers & application developers learning system-level GenAI design

  • Solution and platform architects designing LLM-powered workflows and pipelines

  • Cloud, platform, and backend engineers transitioning into Generative AI engineering roles

  • Startup builders and technical founders exploring AI-native system architecture

  • Professionals preparing for Generative AI Engineer / Applied AI / Architect roles

Not for beginners expecting “easy prompts and chatbots,” or for data scientists seeking a math-heavy course.


Course Features

  • 29+ Hours of Video Content

  • Hands-On Projects and Coding Exercises

  • Real-World Examples

  • Quizzes for Learning Reinforcement

  • GitHub Repository with Solutions

  • Web-Based Course Guide


By the end of this course, you'll be well-equipped to leverage Generative AI for a wide range of applications, from natural language processing to content generation and beyond.


Recent Course Updates

  • Jan 2026 – New section on multi-agent system patterns

  • Sep 2025 – 2 new sections on building agents with LangGraph

  • Aug 2025 – Added lessons on chat models (Subscriber ask)

  • Jul 2025 – Updated MCP content after protocol changes

  • Jun 2025 – Expanded MCP lessons  (Subscriber ask)

  • May 2025 – Model Context Protocol (MCP) section added

  • May 2025 – Python UV environment support

  • Feb 2025 – LLM fine-tuning lessons added (Subscriber ask)

  • Mar 2025 – Multiple curriculum expansions



See more

FAQ

FAQ area empty

Course curriculum

23 chương 269 bài học 28 giờ 15 phút 7 bài học thử miễn phí
Chương 1 Introduction
Chương 2 Setup development environment
Chương 3 Generative AI : Fundamentals
  • Section overview 1:35
  • Intro to AI, ML, Neural Networks, and Gen AI 8:40
  • Neurons, Neural & Deep Learning Networks Học thử 11:51
  • Exercise: Try out a Neural Network for Solving Math Equations 9:52
  • A Look at Generative AI Model as a Black Box 9:15
  • Quiz: Fundamentals of Generative AI Models 4:47
  • An Overview of Generative AI Applications 8:28
  • Exercise: Setup Access to Google Gemini Models 12:20
  • Introduction to Hugging Face 7:24
  • Exercise: Checkout the Hugging Face Portal 9:57
  • Exercise: Join the Community and Explore Hugging Face 4:54
  • Quiz: Generative AI and Hugging Face 5:16
  • Intro to Natural Language Processing (NLP, NLU, NLG) 11:46
  • NLP with LLMs 10:46
  • Exercise: Try Out NLP Tasks with Hugging Face Models 2:28
  • Quiz: NLP with LLMs 3:08
Chương 4 Generative AI applications
  • Section overview 2:50
  • Introduction to OLlama 7:06
  • OLlama model hosting 9:41
  • Model Naming Scheme 3:34
  • Instruct, Embedding, and Chat Models 11:30
  • Quiz: Instruct, Embedding, and Chat Models 3:35
  • Next Word Prediction by LLM and Fill Mask Task 7:48
  • Model Inference Control Parameters 3:26
  • Randomness Control Inference Parameters 10:26
  • Exercise: Setup Cohere Key and Try Out Randomness Control Parameters 3:05
  • Diversity Control Inference Parameters 5:13
  • Output Length Control Parameters 7:18
  • Exercise: Try Out Decoding or Inference Parameters 2:40
  • Quiz: Decoding Hyper-parameters 4:43
  • Introduction to In-Context Learning 12:04
  • Quiz: In-Context Learning 3:33
Chương 5 Hugging Face Models : Fundamentals
  • Section overview 1:38
  • Exercise: Install & Work with Hugging Face Transformers Library 5:48
  • Transformers Library Pipeline Classes 9:50
  • Quiz: Hugging Face Transformers Library 3:35
  • Hugging Face Hub Library & Working with Endpoints 11:04
  • Quiz: Hugging Face Hub Library 3:16
  • Exercise: Proof of Concept (PoC) for Summarization Task 7:22
  • Hugging Face CLI Tools and Model Caching 4:31
Chương 6 (Optional) Hugging Face Models : Advanced
  • Section overview 1:28
  • Model Input/Output and Tensors 6:15
  • Hugging Face Model Configuration Classes 5:48
  • Model Tokenizers & Tokenization Classes 10:03
  • Working with Logits 7:31
  • Hugging Face Models Auto Classes 5:30
  • Quiz: Hugging Face Classes 2:59
  • Exercise: Build a Question Answering System 10:45
Chương 7 LLM challenges & prompt engineering
  • Section overview 2:07
  • Challenges with Large Language Models 11:09
  • Model Grounding and Conditioning 10:52
  • Exercise: Explore the Domain Adapted Models 3:44
  • Prompt Engineering and Practices (1 of 2) 4:49
  • Prompt Engineering and Practices (2 of 2) 6:59
  • Quiz & Exercise: Prompting Best Practices 3:32
  • Few-Shot & Zero-Shot Prompts 4:51
  • Quiz & Exercise: Few-Shot Prompts 5:36
  • Chain of Thought Prompting Technique 7:23
  • Quiz & Exercise: Chain of Thought 4:32
  • Self-Consistency Prompting Technique 5:33
  • Tree of Thoughts Prompting Technique 8:08
  • Quiz & Exercise: Tree of Thought 4:05
  • Exercise: Creative Writing Workbench (v1) 5:09
Chương 8 Langchain : Prompts, Chains & LCEL
  • Section overview 1:28
  • Prompt Templates 7:04
  • Few-Shot Prompt Template & Example Selectors 8:27
  • Prompt Model Specificity 7:06
  • LLM Invoke, Streams, Batches & Fake LLM 9:11
  • Exercise: Interact with LLM Using LangChain 2:51
  • Exercise: LLM Client Utility 4:17
  • Quiz: Prompt Templates, LLM, and Fake LLM 3:30
  • Introduction to LangChain Execution Language 10:07
  • Exercise: Create Compound Sequential Chain 1:42
  • LCEL: Runnable Classes (1 of 2) 6:13
  • LCEL: Runnable Classes (2 of 2) 6:40
  • Exercise: Try Out Common LCEL Patterns 1:24
  • Exercise: Creative Writing Workbench v2 2:04
  • Quiz: LCEL, Chains and Runnables 4:22
Chương 9 Dealing with structured responses from LLM
  • Section overview 1:22
  • Challenges with Structured Responses 8:06
  • LangChain Output Parsers 11:20
  • Exercise: Use the EnumOutputParser 3:49
  • Exercise: Use the PydanticOutputParser 3:46
  • Project: Creative Writing Workbench 4:42
  • Project: Solution Walkthrough (1 of 2) 2:39
  • Project: Solution Walkthrough (2 of 2) 3:56
  • Handling Parsing Errors 9:02
  • Quiz and Exercise: Parsers, Error Handling 3:15
Chương 10 Datasets for model training, and testing
  • Section overview 0:56
  • Datasets for LLM Pre-training 5:47
  • HuggingFace Datasets and Datasets Library 5:59
  • Exercise: Use Features of Datasets Library 7:49
  • Exercise: Create and Publish a Dataset on Hugging Face 2:24
Chương 11 Vectors, embeddings & semantic search
  • What is the Meaning of Contextual Understanding? 8:42
  • Building Blocks of Transformer Architecture 7:18
  • Intro to Vectors, Vector Spaces, and Embeddings 10:11
  • Measuring semantic similarity with distance 6:42
  • Quiz: Vectors, Embeddings, Similarity 3:55
  • Sentence transformer models (SBERT) 5:54
  • Working with sentence transformers 8:45
  • Exercise: Work with Classification and Mining Tasks 4:39
  • Creating embeddings with LangChain 10:50
  • Exercise: CacheBackedEmbeddings Classes 3:15
  • Lexical, semantic, and kNN search 9:26
  • Search Efficiency and Search Performance Metrics 10:53
  • Search Algorithms, Indexing, ANN, FAISS 11:11
  • Quiz & Exercise: Try Out FAISS for Similarity Search 9:27
  • Search Algorithm: Local Sensitivity Hashing (LSH) 7:51
  • Search Algorithm: Inverted File Index (IVF) 7:44
  • Search Algorithm: Product Quantization (PQ) 10:41
  • Search Algorithm: HNSW (1 of 2) 8:40
  • Search Algorithm: HNSW (2 of 2) 11:06
  • Quiz & Exercise: Search Algorithms & Metrics 6:12
  • Project: Build a Movie Recommendation Engine 6:04
  • Benchmarking ANN Algorithms 8:12
  • Exercise: Benchmark the ANN Algorithms 3:16
Chương 12 Vector databases
  • Challenges with semantic search libraries 6:13
  • Introduction to Vector Databases 12:31
  • Exercise: Try out ChromaDB 9:12
  • Exercise: Custom embeddings 1:29
  • Chunking, Symmetric & Asymmetric Searches 9:48
  • LangChain Document Loaders 7:24
  • LangChain Text Splitters for Chunking 9:45
  • LangChain Retrievers & Vector stores 10:20
  • Search Scores and Maximal-Marginal-Relevancy (MMR) 9:38
  • Project: Pinecone Adoption @ Company 3:44
  • Quiz: Vector Databases, Chunking, Text Splitters 4:36
Chương 13 Conversation User Interface
  • Introduction to Streamlit Framework 9:36
  • Exercise: Build a HuggingFace LLM Playground 5:09
  • Building Conversational User Interfaces 7:07
  • Exercise: Build a Chatbot with Streamlit 7:44
  • LangChain Conversation Memory 8:16
  • LangChain chat model classes 12:04
  • Exercise: Try out chat models 1:31
  • Quiz & Exercise: Building Chatbots with LangChain 5:27
  • Project: PDF Document Summarizer Application 3:57
Chương 14 Advanced Retrieval Augmented Generation
  • Introduction to Retrieval Augmented Generation (RAG) 8:49
  • LangChain RAG Pipelines 8:59
  • Exercise: Build Smart Retriever with LangChain 1:57
  • Quiz: RAG and Retrievers 3:25
  • Pattern: Multi Query Retriever (MQR) 5:32
  • Pattern: Parent Document Retriever (PDR) 9:25
  • Pattern: Multi Vector Retriever (MVR) 6:21
  • Quiz: MQR, PDR and MVR 4:36
  • Ranking, Sparse, Dense & Ensemble Retrievers 10:35
  • Pattern: Long Context Reorder (LCR) 6:56
  • Quiz: Ensemble & Long Context Retrievers 4:03
  • Pattern: Contextual Compressor 6:47
  • Pattern: Merger Retriever 4:42
  • Quiz: Contextual Compressors and Merger Retriever Patterns 3:12
Chương 15 Agentic RAG
  • Introduction to Agents, Tools, and Agentic RAG 9:18
  • Exercise: Build a Single-Step Agent without LangChain 9:36
  • LangChain Tools and Toolkits 12:45
  • Quiz: Agents, Tools & Toolkits 4:31
  • Exercise: Try Out the FileManagement Toolkit 1:16
  • How Do We Humans & LLMs Think? 5:14
  • ReACT Framework & Multi-Step Agents 12:09
  • Exercise: Build Question/Answering ReACT Agent 10:18
  • Exercise: Build a Multi-Step ReACT Agent 6:59
  • LangChain Utilities for Building Agentic-RAG Solutions 11:09
  • Exercise: Build an Agentic-RAG Solution using LangChain 5:53
  • Quiz: Agentic RAG and ReAct 6:18
Chương 16 Model Context Protocol (MCP)
  • Section overview 2:07
  • Introduction to Model Context Protocol (1 of 2) 11:08
  • Exercise: Install MCP server on Claude desktop 3:11
  • Introduction to Model Context Protocol (2 of 2) 10:34
  • Quiz: Fundamentals of MCP 2:46
  • Exercise : Setup project with MCP Python SDK 2:55
  • Exercise : Explore MCP using the Inspector tool 4:11
  • Exercise : Code an MCP Server 4:40
  • MCP messaging and transport 12:46
  • Exercise : Setup standalone MCP server with notifications 3:59
  • Quiz: MCP Servers 3:27
  • MCP : Client 5:06
  • Exercise: Code the MCP client 7:18
  • Exercise : Question-Answering application 3:11
  • Quiz: MCP Clients 3:11
  • LangChain MCP adapter library 6:43
  • Exercise: Create tool calling agent with MCP tools 3:44
  • Exercise: Connect with Multiple MCP servers (tools) 2:22
Chương 17 Building workflows & agents with LangGraph
  • Section overview : LangGraph 2:54
  • Static, Intelligent & Agentic workflows (200) 6:19
  • Basics of Langgraph 11:05
  • Building Stateful Workflows 9:00
  • Exercise: Create a stateful graph 8:27
  • Exercise: Working with annotated types (600) 2:26
  • Quiz: Fundamentals of LangGraph 4:03
  • Conditional edges in graphs (700) 7:35
  • Exercise: Working with conditional edges (800) 1:35
  • Exercise: Create loops/cycles with conditional edges (900) 1:16
  • Quiz: Conditions and Loops 2:19
  • Parallel processing & subgraphs (1000) 9:36
  • Exercise : Hands-on with static parallelization (1100) 3:16
  • Exercise: Hands-on with dynamic parallelization (1200) 4:40
  • Working with subgraphs (1300) 4:39
  • Exercise: Hands-on with subgraphs (1400) 4:18
  • Quiz: Parallelization & Subgraphs 3:46
Chương 18 Building workflows & agents with LangGraph
  • Persisting the graph state with checkpointing (1500) 8:45
  • LangGraph checkpointer API (1600) 7:16
  • Try out checkpointers (1700) 2:16
  • Quiz: Persistence & Checkpointers (1725) 2:07
  • Using the memory & storage (1750) 9:40
  • Exercise: Hands-on with storage (1775) 5:38
  • Quiz: Memory & Storage (1780) 2:57
  • Add tool-nodes to the graph (1800) 13:26
  • Exercise: Build a graph with tool nodes (1900) 3:31
  • Exercise: Using MCP Servers from ToolNodes (2000) 2:54
  • Quiz: Tools & MCP Servers (2050) 3:01
  • Creating workflows with Human-in-the-Loop i.e., HITL (2100) 14:06
  • Learn to use static interrupts (2200) 6:34
  • Project: Design a payment workflow with HITL (3000) 5:42
  • Quiz: HITL (3050) 2:01
  • Building agents with LangGraph (3100) 10:05
  • Exercise: Create an agent create_react_agent (3200) 4:48
  • Quiz: Agents with LangGraph (3250) 2:48
Chương 19 Multi Agent Systems : Patterns
  • Section overview - Multi agent systems 1:43
  • Introduction to multi agent systems 11:16
  • Foundational patterns 8:41
  • Exercise: Hands on parallel aggregation pattern 6:49
  • Supervisor & Agent as tool patterns 8:27
  • Exercise: Hands on with Supervisor pattern 4:32
  • Quiz: Multi Agent Patterns #1 3:09
  • Consensus & Swarm-Patterns 9:43
  • Exercise: Hands on with Consensus pattern 5:46
  • LangGraph Swarm Library (900) 3:54
  • Exercise: Hands on- Build Finance Q&A with Swarm 5:01
  • Quiz: Multi Agent Patterns #2 3:34
Chương 20 Fine tuning
  • Introduction to Fine-tuning 4:18
  • Fine-tuning : Reasons 7:14
  • Fine tuning process overview 9:03
  • Tools for fine tuning 9:36
  • Exercise: Fine tune Cohere model for toxicity classification 9:00
  • Creating a dataset for fine tuning 12:04
  • Exercise: Prepare a dataset and fine tune Open AI 4o model 5:41
  • Project: Build a credit card fraud detection dataset 9:19
Chương 21 Dataset preparation for fine-tuning
  • Introduction to Alpaca 9:45
  • Fine-tuning dataset formats 5:01
  • Exercise: Explore instruct fine-tuning datasets 1:34
  • Fine-tuning datasets for chats 5:58
  • Exercise: Prepare chat dataset for fine-tuning 5:52
  • Quiz: Fine-tuning datasets 4:42
Chương 22 Pre-training & Fine-tuning with HuggingFace Trainer
  • Fine-tuning under the covers 10:44
  • Hyperparameters : part 1 of 2 8:18
  • Hyperparameters : part 2 of 2 9:07
  • Understand the checkpointing 3:15
  • Exercise: Explore Hyperparameters 6:40
  • Intro HuggingFace Trainer, Data collator classes 7:12
  • Exercise: Try out the DataCollators 4:04
  • Exercise: Pre-training Roberta model 10:04
  • Exercise: Full fine-tune BERT for sentiment analysis 10:27
  • Quiz: Hyperparameters & Fine-tuning 4:29
Chương 23 Quantization
  • LLM training compute needs 11:03
  • Inferencing compute needs 9:01
  • Quiz : Check your understanding of GPU & CUDA 2:49
  • Introduction to Quantization 8:05
  • Exercise: Quantization maths (Affine technique) 4:03
  • Applying quantization : Static & Dynamic 8:26
  • Exercise: Dynamic quantization with PyTorch 5:02
  • Exercise: Static quantization with AutoGPTQ 4:00
  • Quiz: Check your understanding of quantization 3:24

Requirment

  • Comfortable with basic Python programming

  • Familiarity with APIs, JSON, and software development fundamentals

  • Ability to install tools and work in a local development environment (Windows, Mac, or Linux)

  • No prior machine learning or data science background required

Outcomes

  • Master Generative AI foundations, how LLMs work, and how modern AI systems are designed and applied in real-world products.

  • Design and build end-to-end Generative AI systems using LLMs, retrieval pipelines, tools, and agentic workflows.

  • Implement Retrieval-Augmented Generation (RAG), embeddings, vector search, reranking, and advanced retrieval patterns.

  • Build AI agents, multi-step reasoning systems, and multi-agent workflows using LangChain and LangGraph.

  • Develop production-style applications with structured outputs, validation, memory, and human-in-the-loop workflows.

  • Create MCP servers and clients to connect LLMs to real tools, services, and enterprise systems.

  • Fine-tune and optimize models using Hugging Face workflows, dataset preparation, and quantization techniques.

  • Apply system-level best practices for cost, reliability, scalability, and responsible deployment of GenAI applications.

Instructor

...
Rajeev Sakhuja

0.0

  • ... 0 Student
  • ... 1 Course
  • ... 0 review

View Details

Reviews

Rate this course :

Remove all