AI · Cloud · Systems

Building production-grade distributed systems that hold up under real load.

I write about cloud-native architecture, AI engineering, and the trade-offs that only surface in production.

AI Engineering

Production AI systems — RAG pipelines, evaluation harnesses, and the operational discipline required to ship LLM features that actually hold up in production.

Cloud Architecture

Cloud-native foundations on AWS and Kubernetes: resilient service design, infra-as-code, and platform abstractions that let teams move quickly and safely.

System Design

Distributed systems done carefully — event-driven backends, data consistency, and the trade-offs that only become visible under real load.

Latest writing

All posts →

System DesignJul 10, 2026

AI-Enabled E-Commerce Solutions on OCI

A comprehensive guide to building a production-grade AI e-commerce platform on Oracle Cloud. The architecture's heart is a shared data spine — a product graph and customer 360 kept fresh by change-data-capture — that every AI capability reads from. From discovery (search, recommendations) through conversion (shopping assistant, personalization) to operations (demand forecasting, dynamic pricing, fraud), every capability plugs into the same spine, with the evaluation, logging, and cost model that separate a demo from a production system.

11 min read

System DesignJul 10, 2026

Designing a Content Delivery Network

A system-design walk-through of a CDN, built layer by layer. Start from a single origin, discover why it collapses under load, and add only the mechanism each bottleneck demands — caching, the shield, cache keys, eviction, invalidation, and the tail.

8 min read

System DesignJul 10, 2026

Designing an API Gateway

A system-design walk-through of an API gateway, built layer by layer. Start from clients calling services directly, discover why that breaks, and add only the mechanism each bottleneck demands — a single entry point, then auth, routing, rate limiting, and the discipline that keeps the gateway from becoming the bottleneck it set out to prevent.

9 min read

Featured work

All projects →

2026★ Featured

AI Knowledge Assistant

A production retrieval-augmented assistant for an internal documentation corpus, with eval harness and grounded-answer guardrails.

Cut average support resolution time by 38% with a grounded, evaluated RAG assistant.

TypeScriptPythonLangChainPostgreSQL + pgvector

2025★ Featured

Internal Developer Platform

A golden-path Kubernetes platform with custom controllers that let teams ship services without writing boilerplate manifests.

Reduced mean service onboarding time from days to under 30 minutes.

GoKubernetesTerraformArgoCD