Month 1 Data Foundations, ML Fundamentals & Feature Engineering Weeks 1–4 • 8 Live Sessions
  • Session 1-2: AI/ML Landscape, Roles & Architecture, Python ML Ecosystem, Data Collection, EDA & Visualization.
  • Session 3-4: Statistics, Probability, Hypothesis Testing, Data Cleaning, Feature Engineering & Imputation.
  • Session 5-6: Supervised ML - Regression, Classification, Model Evaluation, Cross-Validation, Bias-Variance Tradeoff.
  • Session 7-8 (Live Hand-Holding): End-to-End ML Pipeline Lab — Build, Train, Validate & Track a Baseline ML Model.
Month 2 Deep Learning, NLP & Computer Vision Weeks 5–8 • 8 Live Sessions
  • Session 9-10: Neural Networks, Backpropagation, Activation, Loss, Optimization, Regularization & PyTorch Fundamentals.
  • Session 11-12: Deep Learning Architectures - CNNs, RNNs, LSTMs, GRUs, Transfer Learning & Fine-Tuning.
  • Session 13-14: NLP Fundamentals, Tokenization, Embeddings, Sequence Models, Transformers Architecture & Hugging Face Ecosystem.
  • Session 15-16 (Live Hand-Holding): DL Applied Lab — Fine-Tune a Transformer Model for Text Classification/NER with Real Data.
Month 3 LLMs, RAG, Vector DBs & Agentic AI Weeks 9–12 • 8 Live Sessions
  • Session 17-18: LLMs Deep Dive, Prompt Engineering, Few-Shot, Chain-of-Thought, System Prompts, Hallucinations & Guardrails.
  • Session 19-20: RAG Architecture - Chunking, Embeddings, Vector Databases (FAISS, Chroma, Pinecone), Hybrid Search, Re-Ranking & Evaluation.
  • Session 21-22: Agentic AI - LangChain, LangGraph, Tool Calling, Function Calling, Memory, Multi-Agent Orchestration, Planning & State Graphs.
  • Session 23-24 (Live Hand-Holding): Production RAG+Agent Lab — Build a Domain-Specific RAG Agent with Tool Use & Streaming Responses.
Month 4 MLOps, LLMOps, Scaling, Monitoring & Capstone Weeks 13–16 • 8 Live Sessions
  • Session 25-26: MLOps/LLMOps Fundamentals - Data/Model Versioning (DVC, MLflow), Experiment Tracking, Reproducibility & Model Registry.
  • Session 27-28: Containerization, Docker, FastAPI Model Serving, Batch/Realtime Inference, CI/CD for ML, Kubernetes Basics & Scaling.
  • Session 29-30: Observability - Monitoring, Drift Detection, Logging, Tracing, Cost Optimization, Security, Governance & Responsible AI.
  • Session 31-32 (Final Capstone & Architecture Defense): Enterprise AI/ML Architect Capstone — Design, Build & Deploy an End-to-End Production AI System with Full MLOps Pipeline.