Advanced · Short courseOnline · live classesOn campus
MLOps: AI in Production
The skills that separate notebooks from products — packaging, deploying, monitoring and retraining ML systems.
Enroll nowApproved & recognised by the University of Mysore
Level
Advanced
Duration
8 weeks
Time commitment
8–10 hrs/week
Format
Live online or on campus
About this course
Most ML never ships. This course is about the last mile: turning models into reliable services. You containerise a model, serve it behind an API, add monitoring for drift and failures, and automate retraining with CI/CD. Everything runs on real cloud infrastructure, and the final project is a deployed, monitored ML service you can show in interviews.
Who it's for: Practitioners who can already train models and want the engineering skills to run them in production.
What you'll learn
Package models with Docker and serve them via FastAPI
Deploy on cloud infrastructure with CI/CD
Version data, models and experiments properly
Monitor drift, latency and failures in production
Design retraining pipelines that keep models honest
Syllabus
From notebook to service
Weeks 1–2- Project structure
- FastAPI model serving
- Docker fundamentals
Deployment
Weeks 3–4- Cloud deployment
- CI/CD for ML
- Secrets and configs
Observability
Weeks 5–6- Logging and metrics
- Data and model drift
- Alerting
Capstone
Weeks 7–8- A deployed, monitored ML service
- Load testing
- Postmortem-style review
Tools you'll use
DockerFastAPIGitHub ActionsMLflowGrafana
Certificate
Finish the course and its capstone project to earn a FuturAIse Academy Certificate of Completion — verifiable online, with the projects to back it up.