<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Harisankar Sivankutty — Notes from the data trenches</title>
  <subtitle>Notes on data engineering and AI engineering — patterns, trade-offs, and hard-won lessons from 10+ years building data platforms and GenAI systems.</subtitle>
  <link href="https://harisankarsivankutty.in/feed.xml" rel="self" type="application/atom+xml" />
  <link href="https://harisankarsivankutty.in/" rel="alternate" type="text/html" />
  <updated>2026-05-25T00:00:00.000Z</updated>
  <id>https://harisankarsivankutty.in/</id>
  <author>
    <name>Harisankar Sivankutty</name>
  </author>
  
  <entry>
    <title>Beyond the API: A Data Engineer&#39;s Guide to the LLM Memory Ladder</title>
    <link href="https://harisankarsivankutty.in/blog/beyond-the-api-data-engineer-guide-to-llm-memory-ladder/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/beyond-the-api-data-engineer-guide-to-llm-memory-ladder/</id>
    <updated>2026-05-25T00:00:00.000Z</updated>
    <summary>What a data engineer learned trying to fine-tune an 8B model — the CUDA crash, the humbling, and the chain of trade-offs that decides whether a model will actually run on the hardware in front of you.</summary>
    <category term="GenAI" />
    <category term="Data Engineering" />
    
  </entry>
  
  <entry>
    <title>From BigQuery to Snowflake: What a Real-World Analytics Migration Actually Looks Like</title>
    <link href="https://harisankarsivankutty.in/blog/from-bigquery-to-snowflake-real-world-analytics-migration/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/from-bigquery-to-snowflake-real-world-analytics-migration/</id>
    <updated>2026-05-23T00:00:00.000Z</updated>
    <summary>The real story of migrating an analytics workload from BigQuery to Snowflake — not the clean version, but the actual trade-offs, surprises, and lessons from doing it inside a live enterprise.</summary>
    <category term="Data Engineering" />
    <category term="Architecture" />
    
  </entry>
  
  <entry>
    <title>Building an Enterprise Data Platform from Scratch: What I Learned Over 9 Months</title>
    <link href="https://harisankarsivankutty.in/blog/building-enterprise-data-platform-lessons-learned/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/building-enterprise-data-platform-lessons-learned/</id>
    <updated>2026-02-10T00:00:00.000Z</updated>
    <summary>Nine months, twenty thousand jobs, petabytes of data. Here&#39;s what I learned building an enterprise data platform from scratch — the architecture decisions, the human dynamics, and six lessons I&#39;d tell myself at the start.</summary>
    <category term="Data Engineering" />
    <category term="Architecture" />
    <category term="AWS" />
    
  </entry>
  
  <entry>
    <title>How AI Agents Work: A Simple Explanation for Non-Technical Readers</title>
    <link href="https://harisankarsivankutty.in/blog/how-ai-agents-work-simple-explanation-non-technical-readers/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/how-ai-agents-work-simple-explanation-non-technical-readers/</id>
    <updated>2026-01-30T00:00:00.000Z</updated>
    <summary>AI agents, memory, tools, and large language models — explained without jargon. A step-by-step breakdown for anyone trying to understand what an AI agent actually is and how it reasons.</summary>
    <category term="GenAI" />
    
  </entry>
  
  <entry>
    <title>Anatomy of a LangChain Application: The Core Components Explained</title>
    <link href="https://harisankarsivankutty.in/blog/anatomy-of-a-langchain-application-core-components-explained/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/anatomy-of-a-langchain-application-core-components-explained/</id>
    <updated>2025-10-14T00:00:00.000Z</updated>
    <summary>A step-by-step walkthrough of building a RAG application with LangChain — from data indexing to retrieval and generation, explained through the core components you&#39;ll use every time.</summary>
    <category term="GenAI" />
    <category term="Data Engineering" />
    
  </entry>
  
  <entry>
    <title>Why LangChain? A Deep Dive into the Essential Framework for GenAI</title>
    <link href="https://harisankarsivankutty.in/blog/why-langchain-deep-dive-essential-framework-for-genai/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/why-langchain-deep-dive-essential-framework-for-genai/</id>
    <updated>2025-10-09T00:00:00.000Z</updated>
    <summary>Why LangChain exists, what fragmentation it solves, and why it became the backbone of enterprise GenAI — a deep dive for engineers who want to understand the framework, not just use it.</summary>
    <category term="GenAI" />
    <category term="Data Engineering" />
    
  </entry>
  
  <entry>
    <title>Building Trust in Data: Productionizing Great Expectations at Scale</title>
    <link href="https://harisankarsivankutty.in/blog/building-trust-in-data-productionizing-great-expectations-at-scale/" rel="alternate" type="text/html" />
    <id>https://harisankarsivankutty.in/blog/building-trust-in-data-productionizing-great-expectations-at-scale/</id>
    <updated>2025-09-20T00:00:00.000Z</updated>
    <summary>How we deployed Great Expectations in production — the challenges, the failures, and what it actually takes to make data validation a first-class citizen in a real pipeline.</summary>
    <category term="Data Engineering" />
    
  </entry>
  
</feed>
