AWS Machine Learning - AI

SEPTEMBER 13, 2024

SageMaker has implemented a robust solution that combines two key strategies: sticky session routing in SageMaker with load balancing, and stateful sessions in TorchServe. Alan Tan is a Principal Product Manager with SageMaker, leading efforts on large model inference. Outside of work, he enjoys the outdoors.

Generative AI 92

Generative AI Applications Artificial Inteligence AWS 92

AWS Machine Learning - AI

AUGUST 8, 2024

The architecture is built on a robust and secure AWS foundation: The architecture uses AWS services like Application Load Balancer , AWS WAF , and EKS clusters for seamless ingress, threat mitigation, and containerized workload management. Saurabh Trikande is a Senior Product Manager for Amazon SageMaker Inference.

Generative AI 122

Generative AI Artificial Inteligence AWS Machine Learning 122

Honeycomb

JULY 12, 2023

While Charity has deep experience in the domains of infrastructure & operations, databases, and backend engineering, I come originally from design, frontend, and product engineering, and I take a particular joy in collaborating with product management and ux design.

Part-Time VPE 98

Part-Time VPE Engineering Technical Review B2C 98

Infinidat

NOVEMBER 11, 2019

3 - Highly available MinIO environment behind NGINX load balancers. . NGINX can balance incoming traffic and spread it evenly across multiple Minio server instances. Gregory Touretsky (@gregnsk) is a Senior Director, Product Management at INFINIDAT. It is also possible to run MinIO within a Kubernetes cluster.

Storage 42

Storage Load Balancer AWS Performance 42

Marcusoft

FEBRUARY 26, 2019

Also we need someone to decided how to distribute the load (aka the load balancer). Should we distribute the load randomly per page request, or should we set up some parts of the application on one server and other parts on another server. It’s not guranteed that the user get to the same server for each new page.

Agile 40

Agile Load Balancer Hardware Examples 40

Modus Create

MARCH 27, 2019

Please refer to the documentation for your web server or load balancer for the specifics. Depending on the tools you use in your environment, the method to block or re-route specific URL paths will be different.

Authentication 75

Authentication Software Review Technical Review Construction 75

LaunchDarkly

JANUARY 17, 2019

For example, a pattern I use when I was at TripIt was we would turn it on for our internal users, like myself as a product manager, our UE designer, make sure everything works to our satisfaction basically doing a UAT, a user acceptance testing. I mean, I’ve been a developer and I’ve been a product manager.

Software Engineering 40

Software Engineering Engineering Software Technical Cofounder 40

AWS Machine Learning - AI

JANUARY 28, 2025

Request batching for bulk operations can also help optimize overall system throughput, though it requires careful balance with response time requirements. Load balancers, queue systems, cache layers, and monitoring systems all contribute to the overall latency budget. He leads the Amazon Transcribe product team.

Artificial Inteligence 71

Artificial Inteligence Generative AI Metrics Applications 71

High Scalability

NOVEMBER 25, 2019

Load Balancers / Reverse Proxy. Deployment Management. There are 200 Engineers(DevOps/OPS/QA/Developers/…), the rest are sales, marketing, support, product management, HR, etc. It's a big team, we have Product managers, UX team, DevOps, scrum teams, architects, engineers performing various roles.

Architecture 21

Architecture Data Center Software Review Systems Review 21