Practical MLOps for Network Operations at Uber
From Telemetry Now by Phil Gervasi
January 22, 2026 · 54 min · Season 2 · Episode 66
About this episode
The episode discusses how Uber utilizes machine learning and MLOps in their network operations, featuring insights from Vishnu Acharya.
Host Philip Gervasi talks with Uber's Vishnu Acharya about how Uber applies machine learning and MLOps to network operations at hyperscale. Vishnu explains Uber’s intentionally simple network design across on-prem and multi-cloud, then shares practical machine learning use cases like predictive capacity planning, hardware failure rate-tracking, and alert correlation to reduce noise and speed mitigation. They also discuss organizational issues, including building blended network/software teams, partnering with internal ML groups, and focusing on service-level outcomes over hype.
People in this episode
Host: Philip Gervasi
Guest: Vishnu Acharya
Topics covered
- MLOps
- network operations
- machine learning
- capacity planning
- hardware failure
- alert correlation
- organizational issues
Keywords
- MLOps
- machine learning
- network operations
- predictive capacity planning
- hardware failure tracking
- alert correlation
- service-level outcomes
Mentioned in this episode
Organizations: Uber
More episodes of Telemetry Now
- Inside Iran’s Internet Blackout · January 9, 2026 · 42 min
- After Maduro: Analyzing Venezuela’s Internet During Political Upheaval · January 6, 2026 · 45 min
- Five AutoCons Later: What’s Really Holding Network Automation Back? · December 5, 2025 · 40 min
- Beyond Chatbots: AI Reasoning at Scale with AI Advisor · November 20, 2025 · 52 min
- What Exactly is a Pre-Sales Engineer? · November 6, 2025 · 34 min
- AutoCon 4 Preview: Network Automation, Intelligence, and the Road Ahead · October 23, 2025 · 39 min
Explore listener stats, chart rankings, contacts and more on the Telemetry Now podcast page.