Published May 21, 2021

Scaling AI in production // Srivatsan Srinivasan // MLOps Coffee Sessions #40

AI thought leader Srivatsan Srinivasan delves into the complexities of deploying machine learning models with Kubernetes, shares expert insights on scaling MLOps within organizations, and reveals his strategic content creation approach for data professionals aimed at advancing edge analytics and IoT.

Episode Highlights

Topics covered

Deployment and Architecture
01
AI Engineering Content
02
MLOps Implementation
03

Scaling AI in production // Srivatsan Srinivasan // MLOps Coffee Sessions #40

Topics covered

Popular Clips

Building MLOps Capability

Kubernetes Hybrid Strategy

Model Deployment Strategies

Model Deployment Patterns

Model Testing Insights

ML Ops Challenges

Bridging ML Gap

MLOps Insights

Testing Challenges

ML Lifecycle Differences

Advanced MLOps Insights

Model Deployment Strategies

Model Deployment Realities

GCP AutoML Overview

Episode Highlights

Deployment and Architecture

AI Engineering Content

MLOps Implementation

Scaling AI in production // Srivatsan Srinivasan // MLOps Coffee Sessions #40

Topics covered

Popular Clips

Episode Highlights

Deployment and ArchitectureSrivatsan Srinivasan explores the intricacies of deploying machine learning models using Kubernetes and the distinct challenges of the ML lifecycle. He highlights the benefits of hybrid strategies and the need for robust architecture in low-latency environments.

Deployment and Architecture

AI Engineering ContentSrivatsan Srinivasan, a leading voice in AI and MLOps, discusses his YouTube channel's focus on advanced content for data professionals. He shares his strategic approach to content creation, emphasizing critical MLOps topics and future plans in IoT and edge analytics.

AI Engineering Content

MLOps ImplementationSrivatsan Srinivasan explores the intricacies of building and scaling MLOps capabilities within organizations. He provides insights into testing, architecture, and deployment strategies essential for effective machine learning operations.

MLOps Implementation