Modern AI Engineering

AI Engineering Bootcamp · Generative AI and LLM course

Generative AI Course: LLMs, RAG, Agents and Production Systems

A generative AI course that goes inside the model and then out to the systems around it. You learn how large language models work, and how to build, serve, evaluate and secure real applications on top of them.

16 modules · 129 video lessons · 28 interactive labs · a quiz in every lesson

What you will learn

  • How large language models work: tokens, embeddings and attention
  • The Transformer architecture, piece by piece
  • Sampling: temperature, top-k and top-p
  • Prompt engineering and context engineering
  • Retrieval-augmented generation (RAG): chunking, embeddings, vector databases, hybrid search and reranking
  • AI agents: tool calling, the agent loop, memory, MCP and multi-agent systems
  • Fine-tuning: LoRA, quantization, distillation, RLHF and DPO
  • LLM inference: KV cache, batching, speculative decoding, vLLM and llama.cpp
  • LLM evaluation, guardrails, prompt injection and AI system design

Who this course is for

  • Software engineers who want to build LLM features and understand why they behave as they do.
  • ML engineers and data scientists who are moving from classic machine learning to generative AI.
  • Technical founders and product people who need to judge what an LLM system can and cannot do.

Course syllabus: 16 modules

  1. Module 1: AI Engineering Starter Kit (1 lessons). Before going deep, we meet the six words that come up in every AI engineering conversation: LLM, RAG, MCP, Agent, Fine-tuning and Quantization.
  2. Module 4: Transformers and How They Think (15 lessons). In this module, we will learn what Generative AI is and how the Transformer, the architecture behind every modern LLM, works from the inside. We will go from tokens to embeddings to attention, one piece at a time.
  3. Module 5: Inside the LLM Output Pipeline (4 lessons). In this module, we will learn how an LLM picks the next token, how we control its creativity, how the output reaches the user token by token, and where the context window fails.
  4. Module 6: Next-Gen LLM Architectures (7 lessons). In this module, we will learn the improvements that modern LLMs add on top of the basic Transformer to become bigger, faster, and able to handle longer inputs. At the end, we will see all of these ideas together inside a real model.
  5. Module 7: The Language Model Zoo (5 lessons). In this module, we will learn that not every language model is a large, text-generating LLM. We will see the smaller, reasoning, recursive, diffusion-based, and decision-only models and when to use which one.
  6. Module 8: Teaching and Shaping Models (11 lessons). In this module, we will learn how a pre-trained model is adapted to our own task, how it is made smaller, and how it is taught to follow instructions and human preferences.
  7. Module 9: The Art of Prompting (5 lessons). In this module, we will learn how to talk to an LLM so that it gives better answers, and how to manage everything that goes into its context window.
  8. Module 10: Building RAG Systems (13 lessons). In this module, we will learn how to give an LLM knowledge that it was never trained on. We will start with how vectors are stored and searched, then move to retrieval techniques, and finally to the advanced forms of RAG.
  9. Module 11: Autonomous AI Agents (16 lessons). In this module, we will learn how an LLM goes from answering questions to actually doing work. We will start with a single agent, see how it uses tools and memory, and then move to systems where many agents work together.
  10. Module 12: Agent Patterns and Frameworks (8 lessons). In this module, we will learn the engineering practices for building reliable agents, and then see how the popular frameworks and coding agents are built.
  11. Module 13: Serving LLMs at Scale (17 lessons). In this module, we will learn how to make LLMs faster and cheaper to run. We will start with what happens during inference, then learn the caching, batching, and speculation techniques, then quantization, and finally the serving engines that put it all together.
  12. Module 14: Measuring What Matters (4 lessons). In this module, we will learn how to measure whether our LLM and our agent are actually doing a good job, and how to see what they are doing in production.
  13. Module 15: Securing AI Systems (3 lessons). In this module, we will learn how to keep an LLM application safe, how attackers try to break it, and how AI-generated text can be identified.
  14. Module 16: Beyond Text: Multimodal AI (6 lessons). In this module, we will learn how AI works with images and other types of data, and the generative models that create images from noise.
  15. Module 17: Production AI Infrastructure (11 lessons). In this module, we will learn the hardware that runs AI models, where to deploy a model, how to send each request to the right model, and how to design a complete AI system end to end.
  16. Module 18: The Edge of AI Research (3 lessons). In this module, we will learn the ideas that are shaping the future of AI, from models that learn an internal picture of the world to systems that improve themselves.

How the course works

  • Every lesson has a video, a written explanation with diagrams, and real code
  • Interactive labs let you change a value and watch the result
  • A 5-question quiz ends each lesson; 4 correct is a pass
  • Run Python in your browser on the Practice page
  • Learn at your own pace and open lessons in any order

Price

Generative AI Engineering: ₹6,599 for one month or ₹9,100 once for lifetime access in India; $71 or $99 elsewhere. Taxes are included. Compare plans.

Frequently asked questions

What will I learn in this generative AI course?

How LLMs work inside, and how to build with them: prompting, RAG, agents, fine-tuning, serving, evaluation and safety.

Do I need machine learning knowledge before generative AI?

It helps but is not required. The track starts with a starter lesson on the core terms. If you want the full foundations, take the Complete AI Engineer track.

Does the course teach RAG and AI agents?

Yes. There are full modules on retrieval-augmented generation and on agents, including tool calling, agent memory, MCP and multi-agent systems.

Is this a prompt engineering course?

Prompt engineering is one module. The course also covers what sits around the prompt: retrieval, tools, fine-tuning, inference and evaluation.

Will I learn to fine-tune an LLM?

Yes. The fine-tuning module covers LoRA, quantization, knowledge distillation, RLHF, DPO and when fine-tuning is the wrong tool.

Other courses