Spotlight

Deploy production generative AI at the edge using Amazon EKS Hybrid Nodes with NVIDIA DGX

Sheng Chen is a Sr. Specialist Solutions Architect at AWS Australia, bringing over 20 years of experience in IT infrastructure, cloud architecture, and multi-cloud networking. In his current role, Sheng helps customers accelerate cloud migrations and infrastructure modernization by leveraging cloud-native technologies. He specializes in Amazon EKS, AWS hybrid cloud services, platform engineering and AI infrastructure.

This tutorial shows how to run production generative AI at the edge by attaching on-prem NVIDIA DGX systems to an Amazon EKS control plane with hybrid nodes, GPU Operator, and NVIDIA NIM.

More articles →

Tools and utilities

  • Zarf: airgapped installation

    Zarf is a tool that simplifies software deployment to Kubernetes clusters in airgapped or disconnected environments.

  • Kogaro – Kubernetes Configuration Hygiene Agent

    Kogaro continuously validates Kubernetes config with 60+ checks across reference, resource, security, image, and network domains, catching silent failures before they impact production.

  • Netfence: eBPF Network Filter Daemon

    Netfence runs as a daemon, injecting eBPF filter programs into cgroups and network interfaces, with a built-in DNS server that resolves allowed domains and populates IP allowlists, and connecting to a central control plane to synchronize network rules.

  • K8s Diagram Generator

    k8s-ingress-gen is a visual diagram builder for Kubernetes resources with bidirectional YAML workflow.

  • Zot: OCI registry

    zot is a production-ready vendor-neutral OCI image registry - images stored in OCI image format, distribution specification on-the-wire

More projects →

Events starting soon

Discover more events onn Kube Events →

The Hidden Cost of Slow Autoscaling
The Hidden Cost of Slow Autoscaling

Forced platform migrations are usually treated as something to survive. At Scout24, a mandatory OS migration became an opportunity to rethink Kubernetes autoscaling, node provisioning, and infrastructure efficiency.

John Ford explains how Scout24 moved its EKS-based Infinity platform from a polling autoscaler and over-provisioned capacity to Karpenter and Bottlerocket. The result was faster node startup, a safer migration path, and about a 30% infrastructure reduction without major downtime.

In this interview:

  • Why two-minute node provisioning forced a 25% capacity buffer
  • How Karpenter made the Bottlerocket migration safer
  • What broke around EC2 metadata, AWS SDKs, and cgroups
  • How the new foundation enables Spot, ARM, and GPU workloads

Learn from production

More case studies →

Matching jobs

    • DevOps Engineer with Ostium Labs

    • Salary: $81K to $297K a year

    • Location: based in the office in New York, NY, USA

    • Tech stack: Kubernetes, ArgoCD, Docker, Terraform, GitHub Actions, Grafana, Prometheus

    • Software Engineer with Canopy

    • Salary: $9 to $484K a year

    • Location: remote from

    • Tech stack: Kubernetes, Docker, Java, Javascript, Python, SQL, Typescript, PostgreSQL, Gitlab

    • Software Engineer with E Source

    • Salary: $100K to $130K a year

    • Location: remote from

    • Tech stack: Kubernetes, AWS, Docker, Java, Python, Cassandra, Jenkins

    • Software Engineer with SWARCO

    • Salary: €39.96K to €143K a year

    • Location: based in the office (and remote from home) in Berlin, DE

    • Tech stack: Kubernetes, Docker, Java, RabbitMQ, Kafka, Jenkins

    • Software Engineer with Scalar

    • Salary: $64.17K to $353.1K a year

    • Location: remote from

    • Tech stack: Kubernetes, GCP, Typescript

Discover more Kubernetes jobs on Kube Careers →

Subscribe to Learn Kubernetes Weekly

Trusted by 77K engineers. Delivered 188 issues and counting.

or subscribe via

Build something

More tutorials →

Call for Papers closing soon

  1. 2

    days

    Open Source Summit Europe 2026

    The Call For Paper is open until 25 June 2026 at GMT-4. More info →
    • Location: Prague, CZ

    • In-person conference organized by Linux Foundation.

    • The conference starts on the 9 October 2026.

    • Apply here
  2. 3

    days

    Kubernetes Community Days Korea 2026

    The Call For Paper is open until 26 June 2026 at GMT-4. More info →
    • Location: Seoul, KR

    • In-person conference organized by KCD South Korea.

    • The conference starts on the 1 September 2026.

    • Apply here
  3. 4

    days

    Kubernetes Community Days Washington DC 2026

    The Call For Paper is open until 27 June 2026 at GMT-4. More info →
    • Location: Washington, DC, USA

    • In-person conference organized by KCD Washington DC.

    • The conference starts on the 15 September 2026.

    • Apply here
  4. 6

    days

    Kubernetes Community Days Nigeria 2026

    The Call For Paper is open until 29 June 2026 at GMT-4. More info →
    • Location: Lagos, NG

    • In-person conference organized by KCD Nigeria.

    • The conference starts on the 24 October 2026.

    • Apply here
  5. 7

    days

    Nerdearla México 2026

    The Call For Paper is open until 30 June 2026 at GMT-4. More info →
    • Location: Mexico City, MX

    • In-person conference organized by Nerdearla.

    • The conference starts on the 20 November 2026.

    • Apply here
  6. 7

    days

    Containerkonferansen 2026

    The Call For Paper is open until 30 June 2026 at GMT-4. More info →
    • Location: Trondheim, NO

    • In-person conference organized by Containerkonferansen.

    • The conference starts on the 15 October 2026.

    • Apply here
  7. 7

    days

    Code Europe

    The Call For Paper is open until 30 June 2026 at GMT-4. More info →
    • Location: Warsaw, PL

    • In-person conference organized by ode Europe.

    • The conference starts on the 15 September 2026.

    • Apply here

Thanks to our sponsors who make Kube Today possible

Find out more about being a sponsor →

More articles

Even more articles →