Module 10: MLOps & Model Deployment
Track, deploy and monitor machine-learning systems with MLflow, FastAPI, Docker and SageMaker.
How to use this module: follow the lessons in order if the stack is new to you, or jump directly to the topic that matches your project. Each lesson includes runnable examples, references and a downloadable notebook.
MLflow Tracking
MLflow Tutorial: Tracking & Model Registry
FastAPI + Docker
Deploy ML Models with FastAPI & Docker
AWS SageMaker
Deploy ML Models on AWS SageMaker
Model Monitoring
ML Model Monitoring & Drift Detection
Practice strategy
Run the examples locally, change one assumption at a time, and record what changes in output, latency, memory or model quality. For production topics, add one failure test before you call the exercise complete.
Next step
Return to the full Data Science curriculum to continue with the next module.
