<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>heissanjay blog</title><description>Personal portfolio and technical writing by Sanjay J, focused on ML systems and infrastructure.</description><link>https://heissanjay.me/</link><language>en-us</language><item><title>From Notebook to Production ML</title><link>https://heissanjay.me/blog/from-notebook-to-production-ml/</link><guid isPermaLink="true">https://heissanjay.me/blog/from-notebook-to-production-ml/</guid><description>A practical workflow for turning experiments into maintainable ML services.</description><pubDate>Sun, 01 Feb 2026 00:00:00 GMT</pubDate><category>ML Engineering</category><category>MLOps</category><category>Systems</category></item><item><title>Evaluation-Driven ML Releases</title><link>https://heissanjay.me/blog/evaluation-driven-ml-releases/</link><guid isPermaLink="true">https://heissanjay.me/blog/evaluation-driven-ml-releases/</guid><description>A release workflow that treats eval quality gates as first-class deployment checks.</description><pubDate>Sun, 18 Jan 2026 00:00:00 GMT</pubDate><category>Evaluation</category><category>Quality</category><category>Release Engineering</category></item><item><title>Observability for LLM Systems</title><link>https://heissanjay.me/blog/observability-for-llm-systems/</link><guid isPermaLink="true">https://heissanjay.me/blog/observability-for-llm-systems/</guid><description>Practical telemetry patterns for tracing retrieval, prompts, and model outputs end to end.</description><pubDate>Tue, 09 Dec 2025 00:00:00 GMT</pubDate><category>LLM</category><category>Observability</category><category>Tracing</category><category>MLOps</category></item></channel></rss>