Thanks for registering

The 2022 cohort is already over!

While the lectures have been released, you shouldn't worry as this is a self-paced course and all the material is available, for free, online.


To participate in the community:

Join us on slack! (join the #serverless-ml_course channel)

Get started with Module 1,2 & 3;

Youtube Playlist

Module 00 (Optional)

Introductions, requirements & Machine Learning 101

  • Lecture 0 - Why Serverless ML? video - slides
  • Lecture 0 - Introduction to the course video
    • What we cover - what we don’t cover
  • Lecture 0 - Development Environment & Platforms video
  • Lecture 0 - Introduction to Machine Learning (ML 101) video

Module 01

How to write Pipelines in Python and run your first Prediction Service

Module 02

Data modelling and the Feature Store. The Credit-card fraud prediction service.

Module 03

Training and Inference Pipelines

Module 04

Analytical vs Operational ML Systems

Module 05

MLOps Principles: Automated Testing, Versioning, Upgrades/Rollback

Module 06

Real-time Machine Learning Systems

Starting Date: 22 Dec 2022
  • Online Inference Pipelines
  • Training/Serving Skew
  • Model Deployments
  • KServe

Key Technologies

Development environment

You can write, test, debug, and train your models in some Python IDE. We will focus on notebooks and Python programs. You can use Jupyter notebooks or Colabatory.


Github to manage your code, GitHub Actions to run your workflows, and Github Pages for your user interface for non-interactive applications. Github Actions offers a free tier of 500 MB and 2,000 minutes to run your pipelines.

Hopsworks has a free tier of 10 GB of storage.

Community newsletetter -

join the community

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.