<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Kubernetes on Rahul Lamba</title><link>https://rahullamba.com/tags/kubernetes/</link><description>Recent content in Kubernetes on Rahul Lamba</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://rahullamba.com/tags/kubernetes/index.xml" rel="self" type="application/rss+xml"/><item><title>sovereign-ai-platform</title><link>https://rahullamba.com/projects/sovereign-ai-platform/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://rahullamba.com/projects/sovereign-ai-platform/</guid><description>&lt;p&gt;sovereign-ai-platform is the platform layer that turns an LLM into a dependable product: an inference gateway, a retrieval pipeline on PostgreSQL + pgvector, an agent/MCP tool surface, a grounding guardrail, and first-class observability — all behind small interfaces so the same image runs offline in CI or in production by changing environment variables only.&lt;/p&gt;
&lt;p&gt;I built it to demonstrate the engineering that real applied AI demands inside regulated, data-sovereign settings (bilingual EN/AR public-sector context): serving within latency and cost budgets, keeping retrieval correct, proving answers are grounded, and keeping confidential data inside the boundary.&lt;/p&gt;</description></item></channel></rss>