We are excited to announce the July meetup scheduled for Thursday, July 16th.
There'll be 2 presentations:
*Scaling AI Workloads on K8S: Reliability Patterns for Production Agentic Platforms
*Using Infrastructure as Code and Securely Synchronizing Credential Secrets from External Services
1st Presentation:
Title: Scaling AI Workloads on K8S: Reliability Patterns for Production Agentic Platforms
Abstract: Running AI agents in production exposes failure modes that traditional microservices never surface. This session draws from real-world experience building and operating an enterprise agentic AI platform on Azure Kubernetes Service — where node pool exhaustion, autoscaling misconfigurations, and invisible queue failures collide with live inference workloads. I’ll cover how to design for horizontal scalability across heterogeneous AI workloads, what signals actually predict cluster saturation before pods go Pending, and a concrete set of reliability patterns: when to use HPA vs KEDA vs Cluster Autoscaler for AI workloads, how to benchmark inference throughput under real load, and what a production-grade control plane looks like when the workload is an agent, not a REST API.
Bio: Jothsna Praveena Pendyala
I am an AI Platform Architect and Senior Data Scientist at Infosys, where I lead the design and operation of an enterprise-scale agentic AI platform on Azure Kubernetes Service and LangSmith. My work spans cloud-native infrastructure, distributed systems reliability, and production observability for AI workloads. I am also an executive member of the ACM Dallas Chapter, an active conference speaker and panel moderator, and a researcher with publications at IEEE and NeurIPS venues.
2nd Presentation: Using Infrastructure as Code and Securely Synchronizing Credential Secrets from External Services
Description:
Securely managing sensitive credentials for service accounts and other external services is essential to maintain a compliant, secure, and reliable environment. I will demonstrate the use of Infrastructure as Code to automate cloud infrastructure provisioning, followed by configuring secure secret synchronization from vaulting providers, such as HashiCorp Vault, into Kubernetes namespaces using the open-source K8s operator External Secrets Operator.
Key takeaway:
You will get an understanding of the basics of Infrastructure as Code and its uses, as well as the process of automating the synchronization of secret credential values from external secrets and Kubernetes environments.
Speaker Bio: Joshua Hupt
6:30 - 6:45 - Social
6:45 - 6:55 - Club Business
6:55 - 7:30 - Scaling AI Workloads on K8S: Reliability Patterns for Production Agentic Platforms
7:30 - 8:30 - Using Infrastructure as Code and Securely Synchronizing Credential Secrets from External Services
8.30 - 8.35 - Social/Wrap-up