diff --git a/app/homelab/page.tsx b/app/homelab/page.tsx index e222939..29538d0 100644 --- a/app/homelab/page.tsx +++ b/app/homelab/page.tsx @@ -2,6 +2,7 @@ import Link from 'next/link' import { ArrowLeft } from 'lucide-react' +import { motion } from 'framer-motion' const skillCategories = [ { @@ -46,18 +47,10 @@ const skillCategories = [ }, ] -const coreCompetencies = [ - 'Multi-tenant GPU scheduling (sm70/Volta constraints)', - 'Zero-downtime GitOps deployments', - 'Service mesh patterns without Istio overhead', - 'Hybrid cloud networking (Cloudflare + bare-metal)', - 'Declarative IAM with OIDC claim mapping', -] - export default function HomelabPage() { return (
-
+
-

- Homelab: Self-Hosted Cloud Platform -

-

- AWS rebuilt from scratch at home—full stack from compute to observability. -

+ {/* Hero */} + +

+ Building AWS at Home +

+

+ A 3-year journey through distributed systems, from Step Functions to LLM inference. +

+

+ There's a difference between knowing how systems work in theory and building them in production. I've spent the last 3 years learning this difference the hard way—first at AWS, then at RBC, and now at home. This is the story of how I learned distributed systems by owning every layer: from workflow orchestration to hardware networking, from GitOps to AI agents. +

+
- {/* Stats */} -
-
-
-
4
-
Nodes
+ {/* Chapter 1: Homelab */} + +
+
+ The Journey
-
-
20+
-
Services
+

+ Homelab: Building AWS from Scratch +

+

May 2025 – Present

+
+ +
+

+ The question: How does LLM serving work at scale? The only way to answer that was to build an entire cloud-like platform with SaaS fundamentals from scratch. 4 bare-metal machines, 1 GPU node, 1 Dell PowerEdge (now in the garage due to noise), and 2 mini-desktops. All running Talos Linux, a Kubernetes-native OS designed for immutability. +

+
+ + {/* Infrastructure section + diagram */} +
+

+ Infrastructure Layer +

+
+

+ 4-node bare-metal cluster (3 control plane + 1 worker) running Talos Linux—immutable, API-driven OS designed for Kubernetes. All wired ethernet to avoid etcd consensus issues. +

+
    +
  • Compute: Talos Linux nodes, machine config via Terraform
  • +
  • Networking: Cilium CNI, nginx ingress, Cloudflare Tunnel for zero-trust external access
  • +
  • Storage: Longhorn for distributed block storage with disk tagging, MinIO for S3
  • +
  • GitOps: ArgoCD with multi-source Applications and sync waves
  • +
-
-
99.2%
-
Uptime
-
-
-
60%
-
LLM Latency Cut
+ + {/* Cluster Topology Diagram */} +
+
+

Talos Cluster Topology

+

Control planes, worker GPU, storage, and networking architecture

+
+
+