This course provides hands-on engineering of Large Language Models (LLMs), focusing on the challenges of building, optimizing, and deploying them. Students will cover the entire lifecycle from: Transformer foundations, GPU scaling,Inference optimization,Fine-tuning Retrieval-augmented generation (RAG) Agentic tool use,Deployment on edge devices, Students will learn through real-world case studies, labs, and projects. By the end, students will be equipped to design production-grade LLM systems for both research and industry applications.

Basics of NLP , Deep Learning, Python Programming

Python, CUDA, Google Colab, AWS Sagemaker (Open source software’s)

• Hands-On Large Language Models: Language Understanding and Generation By: Jay Alammar,
• Maarten Grootendorst Large Language Models: A Deep Dive Bridging Theory and Practice By Uday Kamath et al
• Al Engineering by Chip Huyen
• Various technical blogs