Your cart is empty.
Keep shopping
AI Engineer Core & Agentic Track with RAG, LLM, Agent, QLoRA
Highest Rated
251 students
AI Engineer Core & Agentic Track with RAG, LLM, Agent, QLoRA
Learn AI Engineer Core & Agentic Track with RAG, LLM, Agent, QLoRA and Agentic AI Design Pattern and More
Created bySatish Kothala
Last updated 10/2026
English
French [Auto],
What you'll learn
- Understand Large Language Models (LLMs), transformer architectures, prompt engineering, and model integration to build intelligent AI-powered applications.
- Develop RAG pipelines using embeddings, vector databases, document processing, and semantic search to create context-aware AI applications
- Design and implement agentic AI systems using tools, memory, reasoning, and multi-agent workflows to automate complex tasks and build intelligent AI-driven solu
- Learn parameter-efficient fine-tuning techniques with Quantized Low-Rank Adaptation (QLoRA) to customize large language models
Explore related topics
Course content
80 sections • 405 lectures • 102h 38m total length
Requirements
- You must be curious to learn
Description
The AI Engineer Core & Agentic Track with RAG, LLM, Agent, QLoRA is a comprehensive online course designed to help learners develop practical skills in modern artificial intelligence engineering. This course covers essential AI engineering concepts, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic AI systems, and advanced model fine-tuning techniques using QLoRA. Whether you are a beginner exploring AI engineering or a developer looking to expand your expertise, this course provides a structured learning path to understand and build intelligent AI-powered applications.
You will begin by exploring the fundamentals of Large Language Models, transformer architectures, prompt engineering, and integrating LLMs into real-world applications. You will learn how AI models process information, generate responses, and support intelligent application development. The course introduces practical approaches to working with LLMs and building applications that use generative AI capabilities to solve real-world problems.
Next, you will learn how to build Retrieval-Augmented Generation systems that combine the capabilities of LLMs with external knowledge sources. You will explore document processing, text embeddings, vector databases, semantic search, and retrieval pipelines. These techniques will help you develop AI applications that retrieve relevant information and generate context-aware responses based on specific datasets and documents.
The course also introduces agentic AI development, where AI agents can use tools, maintain context, perform multi-step reasoning, and execute tasks through structured workflows. You will learn how to design AI agents that interact with external systems, automate repetitive tasks, and support more complex problem-solving scenarios. You will also explore how agent-based workflows can be integrated with LLMs and RAG systems to build more capable AI applications.
Finally, you will discover how to fine-tune large language models using Quantized Low-Rank Adaptation (QLoRA). You will understand parameter-efficient fine-tuning, model quantization, and techniques for adapting pretrained models to specialized tasks while reducing memory and computational requirements.
By the end of this course, you will have a solid foundation in AI engineering and a practical understanding of how LLMs, RAG, AI agents, and QLoRA work together. You will be better prepared to develop intelligent applications, experiment with customized language models, automate workflows, and pursue opportunities in AI engineering, generative AI development, and agentic AI application development.
Who this course is for:
- Software Developers
- Anyone wanting to learn Agentic AI and RAG from scratch