Simor
Data Infrastructure for Production AI
Practical writing on AI data engineering, feature stores, and the infrastructure choices that determine whether AI systems work in production.
A new vice president joins the company. Before the first day, the executive assistant delivers a briefing book: the company's history, the current strategic priorities, the key people, the pending dec
The Model Context Protocol (MCP) was released in late 2024 as a standardized way for AI models to interact with external tools and data sources. By mid-2026, the server ecosystem has grown to hundreds
An architecture review for an AI system catches design flaws at the cheapest possible stage: before implementation. A data pipeline that cannot handle the expected volume, a model serving architecture
A video streaming platform grew from 1,000 beta users to 10 million subscribers over thirty months. Their recommendation system was rebuilt three times during this period. Each rebuild was triggered n
Every AI team I have worked with has a graveyard of projects that should have been killed early but were not. A chatbot that no one uses. A recommendation engine that does not outperform a simple heur
Data pipelines break because data producers and data consumers have different assumptions. The producer assumes the consumer can handle null values in a column. The consumer assumes the column is neve
The market for AI engineers is the tightest it has been since the deep learning boom of 2017. Demand has grown 280% year-over-year for the "AI engineer" title, and the supply of experienced practition
Your iPhone prompts you: iOS 18.4 is available. It includes improvements to battery performance, new photo editing tools, and a fix for crashes in third-party apps. You can install it now or wait. If
Basic retrieval-augmented generation works well in demos and poorly in production. The demo shows a clean pipeline: chunk text, embed chunks, retrieve relevant chunks, feed them to the model. The prod