Generative AI Engineering with LLMs Specialization Course Syllabus

Overview: This specialization is designed to equip learners with in-demand skills in generative AI and large language models (LLMs) over approximately 140 hours of content. Spread across six core modules, the course blends theoretical foundations with hands-on labs using industry-standard tools like PyTorch, LangChain, and Llama. Learners will progress at their own pace, dedicating around 4 hours per week, and gain practical experience in building, fine-tuning, and deploying LLMs. The program concludes with a capstone project and includes essential topics such as ethics in AI and career development, preparing participants for roles like AI Engineer, NLP Engineer, and Data Scientist.

Module 1: Generative AI and LLMs: Architecture and Data Preparation

Estimated time: 20 hours

• Introduction to generative AI concepts
• Understanding large language model (LLM) architectures
• Data preparation techniques for training LLMs
• Tokenization and loading text data for model input

Module 2: Generative AI with Large Language Models

Estimated time: 29 hours

• Exploration of transformer-based architectures
• Model training workflows using PyTorch
• Fine-tuning methods for LLMs
• Implementation of Skip-Gram, CBOW, and Seq2Seq models
• Working with RNN-based and Transformer-based models

Module 3: Generative AI Advanced Fine-Tuning for LLMs

Estimated time: 22 hours

• Advanced fine-tuning techniques for LLMs
• Instruction-tuning methodologies
• Introduction to reinforcement learning in LLMs

Module 4: Building Generative AI Applications with LLMs

Estimated time: 20 hours

• Using frameworks like LangChain and Llama
• Developing and deploying NLP applications
• Implementing Retrieval-Augmented Generation (RAG) systems
• Building question-answering NLP systems

Module 5: Ethics and Responsible AI

Estimated time: 22 hours

• Understanding ethical considerations in AI
• Responsible AI practices and model transparency
• Mitigating bias and ensuring fairness in LLMs

Module 6: Final Project

Estimated time: 29 hours

• Capstone project applying learned skills in a real-world scenario
• Design and deployment of a generative AI application
• Comprehensive evaluation and presentation of results

Prerequisites

• Intermediate knowledge of Python programming
• Familiarity with machine learning fundamentals
• Basic understanding of natural language processing (NLP)

What You'll Be Able to Do After

• Tokenize and prepare text data for training large language models
• Deploy and fine-tune LLMs using PyTorch and pre-trained frameworks
• Build and implement NLP applications using Retrieval-Augmented Generation (RAG)
• Apply ethical principles to AI development and deployment
• Develop job-ready skills for roles such as AI Engineer, NLP Engineer, or Data Scientist