<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://tilakparajuli.name.np/feed.xml" rel="self" type="application/atom+xml" /><link href="https://tilakparajuli.name.np/" rel="alternate" type="text/html" /><updated>2026-06-20T12:13:56+00:00</updated><id>https://tilakparajuli.name.np/feed.xml</id><title type="html">Tilak Parajuli | AI/ML Engineer</title><subtitle>I build production AI systems: multi-agent pipelines, RAG, and LLM fine-tuning. Data Scientist at Climate Clean Solutions.</subtitle><author><name>Tilak Parajuli</name><email>tilak.parajuli.58@gmail.com</email></author><entry><title type="html">Hello World</title><link href="https://tilakparajuli.name.np/2026/06/17/hello-world/" rel="alternate" type="text/html" title="Hello World" /><published>2026-06-17T00:00:00+00:00</published><updated>2026-06-17T00:00:00+00:00</updated><id>https://tilakparajuli.name.np/2026/06/17/hello-world</id><content type="html" xml:base="https://tilakparajuli.name.np/2026/06/17/hello-world/"><![CDATA[<p>This is my first blog post. I plan to write about AI/ML engineering, building production systems, and research notes.</p>

<p>Topics I’m thinking about:</p>

<ul>
  <li>Multi-agent architectures and when they actually help</li>
  <li>RAG pipeline design: retrieval quality vs latency tradeoffs</li>
  <li>Lessons from shipping ML in production</li>
  <li>Computational biology and cross-domain ML</li>
</ul>

<p>More to come.</p>]]></content><author><name>Tilak Parajuli</name></author><summary type="html"><![CDATA[First post. Notes on building AI systems, research, and what I'm learning.]]></summary></entry></feed>