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.
Every major model provider has had outages. OpenAI has gone down during peak hours. Anthropic has experienced degraded performance. Google Gemini has had API issues. If your application depends on a s
In 2023, I rewrote a data pipeline three times because the framework landscape kept shifting. First it was built on LangChain. Then the team wanted to switch to LlamaIndex because it handled retrieval
A production AI application calls multiple LLM providers. The primary model is GPT-4o for complex reasoning, but simple classification tasks use Claude Haiku for cost savings, and the fallback for rat
Google announced the Agent-to-Agent protocol, A2A, as a standard for how AI agents communicate with each other. This sits alongside the Model Context Protocol, MCP, which standardizes how agents acces
The first Head of AI Engineering at a company inherits one of three situations. Situation one: there is no AI team, no AI infrastructure, and the mandate is to build from scratch. Situation two: there
Software rollbacks are well-understood. You deploy a new version, detect an issue, and roll back to the previous version. The rollback is atomic: the entire application reverts to the previous state.
France released a fully open-source large language model trained on curated French-language data. India announced a multilingual model covering 22 scheduled languages. The UAE expanded its Falcon mode
A factory quality inspector does not make the widgets. They check the widgets that came off the line. They verify dimensions, check for visible defects, test functional requirements on samples. Their
An AI application built for a single user has no tenancy concerns. The user is the user. There is no data isolation problem because there is only one data set. There is no cost attribution problem bec