Multilingual NLP pipeline up and running from scratch

During this session we will gain hands-on insights on building a multilingual NLP pipeline from the ground up, seamlessly integrated into web applications. Explore the intricacies of setting up the infrastructure on Google Cloud Platform (GCP) and delve into the nuances of NLP model localization. In addition we will talk though the pricing and architectural solutions for being on the budget. Uncover the secrets of dialect resolution and effective slang processing, ensuring your applications are finely tuned for diverse linguistic contexts.

My live recording for the We Are Developers -- https://www.youtube.com/watch?v=_AYr4fqd0Yg&t=7409s

Speed Up Microservice Setup with Composable Approach

Imagine how good it would be to have a magic button that allows you to set up and integrate a brand-new microservice in your ecosystem in XX minutes. Infrastructure, CI/CD, and basic code snippets all in one.

This talk aimed to familiarize you with the composable approach, which is as close to the "magic button" as possible.

In this session, we'll walk you through how Terraform conjures infrastructure like magic, shared workflows streamline processes, and Maven archetypes simplify code generation.

As the cherry on top -- live demo of the accelerator approach with Google cloud platform.

Here is the sample of slides for this topic -- https://drive.google.com/file/d/1CcjJ6xHxZufpf-WSKrILBx_KB7R5IEm-/view?usp=sharing

and the how I delivered the same topic before: https://youtu.be/MIPN9ycwinQ?feature=shared

K8s E-commerce Cookbook for Devs: Dos, Don'ts and Please Never Again Edition

Point of endless pain in e-commerce: how to enable your teams to have full ownership over the deployment process. A lot was said and done on this topic, maybe even a little too much. So to make a long story short, let's do a speed run over the real-life success (but sometimes not) stories.

We're going to discuss how to simplify and compose the CICD process with the power of Crossplain, K8s, and ArgoCD. We will examine each component of composable flow that with minimum effort needed for extension and scale

3+1 ways to do MlOps with Kubernetes

What happens with models after they are trained? "Whatever they were meant for," you would say, and you would be completely right. However, what also awaits around the corner are tons of questions like: How to deploy? Where to deploy? How to scale? And, of course, how to limit the budget to a reasonable paycheck?

And here it comes: K8s could save our lives again, and in this session, we will explore 3 and 1 additional K8s-based tools to manage your MLs effectively! All of them we will test against a custom LLM model for performance, scalability and user-friendly deploy process of course!