DataTalks.Club Meetups Global

The new cohort of Machine Learning Zoomcamp 2026 starts today.

​In this launch session, course creator Alexey Grigorev will help you get oriented before the first videos, notebooks, homework, and project ideas start piling up. The goal is simple: leave the session knowing what to do first, what matters most, and how to avoid turning the course into a folder of unfinished notebooks.

## ​What We'll Cover

​Alexey will walk through:

• ​The journey: from ML basics and tabular models to deployment, deep learning, serverless inference, Kubernetes, and model serving
• ​The first week: how to approach the intro module, setup, notebooks, and homework without overcomplicating things
• ​The rhythm of the cohort: weekly work, deadlines, scoring, leaderboard, peer review, and certificates
• ​The project path: how the midterm and capstone help you turn course work into portfolio work
• ​The support system: Slack, Telegram updates, FAQ, learning in public, and how to ask useful questions

​There will also be time for live questions, so bring whatever is on your mind: prerequisites, time commitment, project ideas, or how to catch up if life gets busy.

## ​Starting ML Zoomcamp?

​ML Zoomcamp is a free 4-month course for people who want to become practical machine learning engineers. You'll learn the full flow: prepare data, train models, evaluate them, deploy them, and package the work clearly enough that other people can run it.
​You should be comfortable with:

• ​programming
• ​the command line
• ​Git
• ​Docker basics

​You don't need:

• ​previous machine learning experience
• ​advanced math
• ​cloud experience
• ​a degree

​The cohort starts on 14 September 2026. If you haven't joined yet, you can register here.
​

## ​About the Speaker

​Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series.

​He has worked in software engineering and machine learning for more than 10 years, built ML systems in production, authored technical books including Machine Learning Bookcamp, and helped thousands of learners through DataTalks.Club courses.

Join our Slack: https://datatalks.club/slack.html

​In this hands-on workshop, we’ll build a multi-agent workflow with Switch, an open-source workspace where people and AI agents can coordinate real work through governed rooms. We’ll start with a real use case, connect multiple agents, and work through the solution live to see how agents can coordinate with people while maintaining shared context.

​We’ll cover the following steps:

• ​Define a real-world workflow that benefits from people and AI agents working together.
• ​Build the workflow in Switch, bringing existing agents into a shared room and putting them to work alongside people.
• ​Keep context with the work, exploring how rooms preserve context and history as people and agents join, leave, and hand off work.

​By the end of the workshop, you’ll be able to build your own AI agent workflow in Switch, bring existing agents into a shared room, and use persistent context and history to keep people and agents working together.

​About the speaker:
​Louis is an AI engineer at SandboxAQ, the parent company behind Switch. He and his team built Switch to solve a problem they experienced firsthand: as they adopted more AI agents across different tools and frameworks, putting those agents to work across a team required new integrations and repeated context sharing. Switch grew out of that need, bringing people and agents together within the collaboration tools teams already use while preserving context and history of the work.

​This event is sponsored by SandboxAQ.

Join our Slack: https://datatalks.club/slack.html