AI Journey Path

FOUNDATION

01 CPU, GPU, CUDA, Tensor, PyTorch 02 Matrices, weights, bias 03 Neural networks 04 Training vs inference 05 Build tiny neural network

MACHINE LEARNING

06 Dataset, features and labels 07 Regression and classification 08 Train / validation / test 09 Evaluation metrics 10 Build a simple ML model

GENAI

11 Transformers 12 Hugging Face 13 Run local LLM 14 Embeddings 15 Vector DB 16 RAG 17 Agents + MCP

MLOPS

18 MLflow experiment tracking 19 Model artifacts & registry 20 Data/model versioning 21 Dockerize model 22 CI/CD for ML 23 Model serving 24 Kubernetes + GPU workloads 25 Azure Databricks / Cloud MLOps

PRODUCTION

26 Model monitoring 27 Drift & model quality 28 OpenTelemetry GenAI 29 Langfuse 30 Grafana AI observability

CAPSTONE

31 End-to-end production AI/MLOps project