<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Engineering Production AI</title><description>ML inference, distributed systems, and MLOps engineering notes by Lokesh Jain.</description><link>https://engineering-production-ai.pages.dev/</link><item><title>Designing Scalable ML Inference Pipelines</title><link>https://engineering-production-ai.pages.dev/articles/designing-scalable-ml-inference-pipelines/</link><guid isPermaLink="true">https://engineering-production-ai.pages.dev/articles/designing-scalable-ml-inference-pipelines/</guid><description>From model execution to production systems: batching, scheduling, GPU efficiency, reliability, and observability.</description><pubDate>Thu, 22 Oct 2026 00:00:00 GMT</pubDate></item></channel></rss>