Tiago Reichert
Principal Specialist SA, AppMod
São Paulo, Brazil
Actions
Tiago is a Principal Solutions Architect at AWS, where he helps companies across Latin America optimize their container and cloud strategies while leading the Containers Tech community across the region. With more than 10 years of experience in technology, he is passionate about GenAI, SaaS, and Platform Engineering. Beyond his role at AWS, he is an active contributor to the cloud-native ecosystem, serving as an organizer of KCD Brazil and other local meetups focused on advancing cloud-native technologies. He has spoken at major industry events including AWS re:Invent, KubeCon, and PlatformCon. He has also contributed to the ecosystem through open-source projects, technical blogs, workshops, and white papers, in addition to being a Platform Engineering Ambassador and CNCF Ambassador.
Links
Badges
Area of Expertise
From Pull to Predict: Accelerating AI Model Deployment from minutes to seconds on Kubernetes
In the era of large AI models, deployment latency and resource utilization present significant challenges for Kubernetes operators. This session demonstrates techniques to reduce model startup times and optimize cluster resources. We'll deploy a 7B parameter LLM using Ray and vLLM for scaling and serving, implementing three key optimizations: SOCI (Seekable OCI) for lazy loading of container images, enabling containers to start without downloading the entire image first; an optimized storage layer that keeps models pre-downloaded and ready for quick access; and intelligent node provisioning using Karpenter for dynamic resource allocation. We'll compare a standard deployment against one using these optimizations, showing the differences in startup times, resource usage, and operational costs. Attendees will learn implementation steps for these techniques, which they can apply to their own Kubernetes environments to improve AI model deployment efficiency.
Reduzindo Custos e Aumentando a Eficiência com Karpenter e KEDA no Kubernetes
Vamos explorar como integrar Karpenter e KEDA para aprimorar o dimensionamento de aplicações no Kubernetes. O Karpenter otimiza o gerenciamento do cluster ao selecionar e consolidar os tipos de instâncias, como Spot e Graviton, para reduzir custos e aumentar a eficiência. Simultaneamente, o KEDA (Kubernetes Event-Driven Autoscaling) oferece dimensionamento dinâmico baseado em eventos ou métricas personalizadas, como a quantidade de mensagens em um tópico Kafka ou métricas do Prometheus. Participe para descobrir como essas ferramentas podem trabalhar juntas para maximizar o desempenho e a eficiência da sua infraestrutura na nuvem.
Streamline Kubernetes Deployments with Helm, GitOps, and Terraform for SaaS
Engineers often face challenges in reusing code, slowing delivery. GitOps, Terraform, and Helm can offer standardized and reusable assets, streamlining application deployments alongside infrastructure components enabling governance and reducing toil.
From Chaos to Control: Structuring Repositories for Scalable GitOps on Kubernetes
As Kubernetes adoption grows, maintaining consistency across clusters becomes increasingly challenging, especially during upgrades. Kubernetes upgrades can be complex due to several factors, such as managing dependencies on specific add-on versions and handling deprecated and removed API versions.
This session addresses repository standardization within a GitOps framework. Join us to explore best practices for organizing repositories to improve upgrade management and consistency across Kubernetes environments. We’ll examine different approaches, from MonoRepo strategies (for all components or just add-ons) to a repo-per-cluster setup, comparing the pros and cons of each. Using Fluxv2, Kustomize, OpenTofu, and Helm, we’ll provide real-world examples that illustrate how centralized repository organization enhances Kubernetes GitOps, helping attendees streamline application and add-on deployments, manage variables across clusters, and maintain consistent versions.
From Logs to Insights: Real-time Conversational Troubleshooting for Kubernetes with GenAI
In today’s distributed microservices landscape, Kubernetes environments generate vast volumes of logs, making troubleshooting complex and time-consuming. Operators often sift through massive data to identify issues, leading to prolonged downtime—a challenge that intensifies with multiple clusters. Discover how GenAI optimizes troubleshooting by transforming traditional logs into conversational insights. This session covers building an AI-driven observability solution with Large Language Models (LLMs). We start by configuring Fluent Bit collectors to gather systemd logs, Kubernetes events, and application logs, which are then streamed to a scalable object storage. By constructing a vector database, we enable users to query and interact with logs in natural language. We will provide a step-by-step guide that equips attendees with actionable knowledge to implement GenAI observability in their Kubernetes clusters.
Engenharia de Plataforma com Kubernetes: DevOps para Aplicações Multi-tenant
Aplicações SaaS e microsserviços distribuídos exigem uma mudança no gerenciamento e implantação de infraestrutura, tornando a automação crucial. Ambientes multi-tenant frequentemente requerem múltiplas réplicas da mesma aplicação em diferentes configurações para atender requisitos diversos dos clientes. Nesta sessão, abordaremos ferramentas open-source do ecossistema Kubernetes para suportar o provisionamento, implantações faseadas e contínuas de novas versões da aplicação e remoção de tenants. Vamos demonstrar como essas ferramentas podem atender às nuances e necessidades únicas dos ambientes multi-tenant com uma solução end-to-end que utiliza GitOps, Flux, OpenTofu Controller, Argo Workflows e Helm.
Accelerating Application Delivery with OpenTofu Controller and GitOps
Developers often face challenges in reusing code and infrastructure across different projects, leading to duplication of effort and slower time-to-market. Platform engineering aims to solve this by providing a shared, standardized platform with reusable assets, automation, and governance, enabling faster development and delivery of applications.
Explore how OpenTofu Controller, in conjunction with Fluxv2 and GitOps principles, enables a seamless integration of infrastructure and application resources within a Kubernetes environment. We will dive into a real-world use case, showcasing the deployment of a multi-tenant SaaS platform on Kubernetes using OpenTofu Controller and Helm to consistently package reusable assets and deploy both application definitions and infrastructure components through a Git-centric workflow.
Empowering Platform Engineering: Unleashing the Potential of KubeVela and Crossplane.
Explore the implementation of OAM with KubeVela and Crossplane to streamline development, bolster security, and facilitate scalable infrastructure management.
KubeCon + CloudNativeCon North America 2025 Sessionize Event
PlatformCon 2025 Sessionize Event
CNCF-hosted Co-located Events Europe 2025 Sessionize Event
CNCF-hosted Co-located Events North America 2024 Sessionize Event
AWS Community Day Brasil 2024 Sessionize Event
PlatformCon 2024 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top