This week on towards scaling inference, we chat with Sushant Hiray, Director of Machine Learning, RingCentral. 

During the episode, Sushant talks about his experience building their ML infrastructure from the ground up, ideas to overcome challenges during the deployment process, and implication of infrastructure cost on business outcomes alongside best practices for other ML practitioners & researchers who are in the process of ML deployment in production.

Introduction: 00:00
Business problems solved through AI: 02:15
Process of ML Model deployment: 03:11 
Challenges faced in deploying in Kubernetes: 03:50
Techniques for optimization before deployment: 06:06
Role of Networking in managing Kubernetes: 10:31
Memory sharing for GPUs on Kubernetes: 13:25
Implication of Infrastructure cost on business outcomes: 16:25
Best practices for ML practitioners: 19:31

Inferless Transcript on Youtube

ML Model Deployment in Kubernetes with Sushant Hiray from RingCentral