IRL & Online Program
Generative AI Mastery
Master Large Language Models, prompt engineering, and build custom generative AI solutions from scratch.
Hands-on Highlights
- Implement a production-grade RAG pipeline
- Fine-tune Llama 3 using PEFT and LoRA
- Build AI agents with LangChain and AutoGen
- Deploy open-source LLMs using vLLM
Detailed Syllabus
Week 1-2
LLM Foundations & Prompt Engineering
- Understanding decoder-only architectures
- Advanced prompt engineering techniques (Zero-shot, Few-shot, CoT)
- OpenAI API and tokenomics
- Prompt testing and evaluation
Week 3-4
Vector Databases & RAG
- Semantic search and embedding models
- Setting up Pinecone/ChromaDB
- Building a Retrieval-Augmented Generation (RAG) system
- Handling chunking strategies and hybrid search
Week 5-6
Agentic AI & Tool Calling
- Introduction to LangChain and LlamaIndex
- Function calling and tool integration
- Building multi-agent systems with AutoGen
- Memory management for conversational agents
Week 7-8
Fine-Tuning & Deployment
- Parameter-Efficient Fine-Tuning (PEFT) and LoRA
- Instruction tuning Llama 3 on custom data
- Model quantization (GGUF, AWQ)
- Deploying with vLLM and FastAPI
Target Roles & Career Paths
Generative AI Engineer
LLM Developer
Prompt Engineer
AI Solutions Architect
These are the primary roles you will be equipped to apply for upon successful completion of the course and portfolio projects.