---
title: "Discussion on \"How Uber Runs 30 Million ML Predictions Per Second on Kubernetes\" | Hashnode"
description: "Discussion on \"How Uber Runs 30 Million ML Predictions Per Second on Kubernetes\". The architecture behind Michelangelo and what every engineering team can learn from it\nPublished by Insigh8s · Tech Stories · KubeCon EU 2026 Amsterdam\nAt KubeCon EU 2026 in Amsterdam, When I heard 30"
url: "https://hashnode.com/posts/tech-stories-how-uber-runs-30-million-ml-predictions-per-second-on-kubernetes/69ce48e10ff860b6de99cc8c"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [How Uber Runs 30 Million ML Predictions Per Second on Kubernetes](https://blog.insigh8s.io/tech-stories-how-uber-runs-30-million-ml-predictions-per-second-on-kubernetes?utm_source=hashnode&utm_medium=feed)

The architecture behind Michelangelo and what every engineering team can learn from it Published by Insigh8s · Tech Stories · KubeCon EU 2026 Amsterdam At KubeCon EU 2026 in Amsterdam, When I heard 30

Apr 2 · 14 min read · blog.insigh8s.io  
Read the article

## Written by

[Ashutosh Rathore](https://hashnode.com/@ashutoshrathore)

@ashutoshrathore · Tallinn Estonia

  
[View profile](https://hashnode.com/@ashutoshrathore)

DevOps | Infrastructure | Cloud | Automation

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
