Session
Routing ML Inference Traffic at Internet Scale
Learn how traffic routing for ML Models poses unique challenges at internet scale, and how Netflix solves them through specialized software design patterns. Learn how various API Gateway solutions (REST), Service Mesh, and custom design can help scale traffic routing for efficient ML model serving. We will also briefly go into how various experiences on Netflix.com are powered by unique ML Models.
Here is the recent official blog post on this topic that I recently co-authored at Netflix.
https://netflixtechblog.com/state-of-routing-in-model-serving-16e22fe18741
Rajat Shah
Staff Software Engineer, AI Platform, Netflix
San Francisco, California, United States
Links
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top