From DevOps to MLOps: Scaling ML models to 2 Million+ requests per day

The challenge with Machine Learning (ML) models is productionizing. It requires data ingestion, data preparation, model training, model deployment, and monitoring.Adopting MLOps practices is similar to DevOps practices. In MLOps, the workload changes, but some core principles like automation, continuous integration/continuous deployment (CI/CD), and monitoring. Taking DevOps practices, I will discuss the similarities and differences in adopting MLOps practices.In this talk, Chinmay takes a production use case to scale ML models to 2 million+ daily requests. It leverages Google Cloud's (GCP) infrastructure to use its GPU and other services. This talk will help you draw similarities between DevOps and MLOps as a DevOps practitioner and help you learn how to run Machine Learning models at the production scale with best practices.

Related Talks

You've Got the Cloud All Wrong, Let's Fix That!

Most people think the cloud is just files floating in the sky.Spoiler: it's not.In this episode, I’m breaking down what “the cloud” really is, why everything you’ve been told is probably wrong, and why it's the engine behind everything from Netflix to AI to your online checkout.This is the kickoff to WTH is the Cloud?! a fun series that makes cloud technology make sense.

Learn More
Learn More
WTH is Chaos Engineering?! A Quick Look at Breaking Things on Purpose

Ever wonder why some teams intentionally break their own systems? Welcome to the world of chaos engineering — a practice that's not just for Netflix-scale infrastructure, but for any team that wants to build resilient, reliable applications.In this session, we'll demystify chaos engineering and explain why intentionally breaking things is actually the smart move. You'll learn:What chaos engineering really is (in plain English, no buzzwords)Why waiting for production failures is a terrible strategyHow to start experimenting with controlled failure locally, before it happens in the wildReal-world examples of chaos experiments that catch bugs you'd never find in traditional testingTools and techniques to get started without blowing up your infrastructureThrough practical demos using LocalStack's cloud emulation and chaos engineering tools, we'll simulate failures like network latency, service outages, and resource exhaustion right from your laptop.If you've ever said "it worked on my machine" only to watch it crash in production, this talk is for you—let's break things intentionally so they don't break unexpectedly.

Learn More
Learn More
Wait, Building in the Cloud Is This Complicated?

Testing in the cloud = slow builds, fragile staging, surprise bills.Let’s talk about how developers are flipping the script and using local cloud environments to test smarter, faster, and cheaper — without breaking production.Bonus: You’ll learn how LocalStack lets you simulate AWS on your machine. Game changer.

Learn More
Learn More

Launch yourself in the world of local cloud development

Try for free
Try for free
Talk to Sales
Talk to Sales