Repolode
Submit
DataTalksClub

DataTalksClub/mlops-zoomcamp

A free, self-paced 9-week online course covering MLOps: experiment tracking, orchestration, deployment, monitoring and best practices.

View on GitHubWebsite
Stars
15,450
Forks
3,072
Open issues
4
Last commit
5 days ago

What is it?

MLOps Zoomcamp is a free course from DataTalks.Club that teaches how to take machine learning models from training and experimentation into production and keep them running reliably. It is organized as six modules with video lectures, homework and a final end-to-end project.

The syllabus covers experiment tracking and model management with MLflow, workflow orchestration and ML pipelines, and model deployment for both online web services (Flask) and streaming or batch scoring. Monitoring modules use Prometheus, Evidently, Grafana and Prefect, and the best-practices module covers testing, linting, GitHub Actions CI/CD and Terraform.

The course is fully available for self-paced study, with all materials hosted in this repository. Prerequisites include Python, Docker, command-line basics and prior machine learning experience, such as the companion ML Zoomcamp course.

Key features

  • 01Covers experiment tracking and model registry with MLflow.
  • 02Teaches workflow orchestration and ML pipelines with Prefect.
  • 03Shows model deployment as web services, streaming on AWS Kinesis and Lambda, and batch scoring.
  • 04Includes monitoring with Prometheus, Evidently and Grafana.
  • 05Covers testing, linting, GitHub Actions CI/CD and Terraform.
  • 06Ends with a final project that combines the full pipeline.

Use cases

  • Data scientists learning to move models from notebooks into production.
  • ML engineers who want a structured curriculum on deployment and monitoring.
  • Software engineers building a portfolio project around MLOps practices.

Quick start

  1. 1

    Open the course materials on GitHub

  2. 2

    Watch the video lectures on the YouTube playlist

  3. 3

    Join the Slack channel to ask questions and share progress

Things to know

  • No live cohort is planned for 2026, so you study self-paced.
  • Self-paced homework is self-checked and not scored, and there is no certificate or peer review.

Topics

#mlops#machine-learning#course#model-deployment#model-monitoring#workflow-orchestration#mlflow

FAQ

What is mlops-zoomcamp?
A free, self-paced 9-week online course covering MLOps: experiment tracking, orchestration, deployment, monitoring and best practices. MLOps Zoomcamp is a free course from DataTalks.Club that teaches how to take machine learning models from training and experimentation into production and keep them running reliably. It is organized as six modules with video lectures, homework and a final end-to-end project.
Is mlops-zoomcamp free to use? What license does it have?
mlops-zoomcamp has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
Is mlops-zoomcamp still maintained?
Actively maintained. The last commit to mlops-zoomcamp was on Oct 15, 2026.
What can I use mlops-zoomcamp for?
Data scientists learning to move models from notebooks into production. ML engineers who want a structured curriculum on deployment and monitoring. Software engineers building a portfolio project around MLOps practices.
How do I install mlops-zoomcamp?
Open the course materials on GitHub Watch the video lectures on the YouTube playlist Join the Slack channel to ask questions and share progress
Where can I get mlops-zoomcamp?
The source code and installation instructions are on GitHub: https://github.com/DataTalksClub/mlops-zoomcamp

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects