<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Samama Usman</title><description>Backend engineer working on ML systems and LLM inference — making models run faster and cheaper at the serving layer. CS undergrad at NUST, Islamabad. Writing about GPU programming and inference internals.</description><link>https://samamausman.com/</link></channel></rss>