Technical Deep Dives & Product Explorations

This site hosts long-form, practical analyses of cloud platforms, distributed systems, and developer tooling — focused on architecture, trade-offs, and real-world fit.

Read the blog About me

Latest posts

Deploying Llama 3.1 8B on RHOAI with Helm: a ServingRuntime, a PVC, and two debugging sessions

A from-scratch Helm chart that deploys meta-llama/Llama-3.1-8B-Instruct on Red Hat OpenShift AI via a custom vLLM ServingRuntime and a KServe InferenceService — plus the two…

Aug 18, 2026

Challenges of serving LLMs: will the model even fit on your GPU?

Before you pick an inference server, a GPU, or a cloud bill, you need to answer one question: how much memory does this model actually need? This post walks through…

Jul 6, 2026

ABOM: a bill of materials for AI agents — block the action, sign the proof, hand it to the auditor

AI agents now take consequential actions inside regulated systems, but nobody can say in one signed document what an agent is made of, what it’s allowed to do, or prove what…

Jun 24, 2026

Installing Red Hat OpenShift AI Self-Managed 3.4(latest) in Red Hat Openshift 4.22(latest) on AWS: A Shell-Based Guide

A compact, annotated shell steps to install Red Hat Openshift AI on OpenShift 4.22 (latest version) on AWS - with a ready-to-edit install-config.yaml, sensible defaults, and…

Jun 10, 2026

Browse all posts →