From Black Box to Glass Box: Teaching Developers Tracing with New Relic Segments

Distributed systems often feel like a black box we know something is happening inside, but we can’t see where time is being spent or what’s going wrong. This session turns that black box into a glass box by showing developers how to implement tracing with New Relic segments. You’ll learn how to instrument applications effectively, gain visibility into downstream calls, and make sense of performance bottlenecks. Whether you’re new to observability or looking to deepen your tracing practices, this talk will provide practical steps and examples you can apply immediately in your services.

Inferencing LLMs in production with Kubernetes and KubeFlow

Large Language Models (LLMs) are powerful but deploying them reliably, cost-effectively, and at scale in production is a different challenge altogether. In this session, we’ll walk through how to operationalize LLM inference using Kubeflow on Kubernetes, leveraging open-source and cloud-native tools to build resilient, scalable, and observable GenAI infrastructure.

We'll cover:

Architecture for serving LLMs using KServe or vLLM on GKE

Strategies for optimizing latency, GPU usage, and autoscaling with KEDA, Triton, or Multi-Model Serving

Integrating Kubeflow Pipelines for pre/post-processing, caching, and batch inference workflows

Let’s Talk to Your Cluster: LLM Agents Powered by Kubernetes MCP Server

Lessons from Running a CNCF Community: Mistakes, Wins, and Growth

Building a CNCF community comes with wins and challenges. We launched KCD Sri Lanka in 2022 with a high-grade green screen production, featuring global speakers and over 1K YouTube livestream views. In 2023, our in-person KCD Sri Lanka was an early sold-out, house-full event, drawing speakers from around the world.

From securing sponsorships and growing engagement to handling setbacks, we’ll share key lessons from leading Kubernetes Sri Lanka. Whether you’re starting or scaling a CNCF community, this talk will provide practical takeaways to build a sustainable and impactful cloud native ecosystem.

Surfing the Waves of CI/CD: GKE, ArgoCD, and GitHub Actions

In this talk, we'll explore the exciting world of Continuous Integration and Continuous Delivery (CI/CD) by likening it to surfing the waves. Just as surfers need skill, balance, and the right equipment to ride the waves successfully, software developers need the right tools and practices to navigate the complexities of CI/CD.

Automating Microservice Scaling with KEDA and Google Vertex AI Predictions

In today's dynamic cloud-native environments, scaling microservices efficiently is key to optimizing performance and resource management. This talk explores how to automate microservice scaling using KEDA (Kubernetes Event-Driven Autoscaling) and predictive insights from Google Vertex AI. I will demonstrate how to leverage Vertex AI predictions to dynamically adjust workloads based on demand, ensuring efficient resource utilization while maintaining application performance.