---
title: "SriSumukha S (@sumukha) | Hashnode"
description: "ML Engineer · GraphRAG · MLOps · AWS. Read the latest articles by SriSumukha S on Hashnode."
url: "https://hashnode.com/@sumukha"
---

@sumukha

# SriSumukha S

@sumukha · Tokyo, Japan · Joined March 2026

ML Engineer · GraphRAG · MLOps · AWS

### [The NLP Pipeline Behind Insight Engine: Extracting 10.7M Entities from 229K Research Papers (Part 2)](https://sumukha87.hashnode.dev/the-nlp-pipeline-behind-insight-engine-extracting-10-7m-entities-from-229k-research-papers-part-2?utm_source=hashnode&utm_medium=feed)

How I used spaCy, SciSpacy, and a rule-based relation extractor to extract 10,779,699 entities and 2,294,895 relationships from 229,498 arXiv papers — fully tracked with DVC and MLflow on a single RTX 4060 GPU.

7 min read · [sumukha87.hashnode.dev](https://sumukha87.hashnode.dev/the-nlp-pipeline-behind-insight-engine-extracting-10-7m-entities-from-229k-research-papers-part-2?utm_source=hashnode&utm_medium=feed)

[Mar 25](https://hashnode.com/posts/the-nlp-pipeline-behind-insight-engine-extracting-10-7m-entities-from-229k-research-papers-part-2/69c3b4578a263e79cb21fa63)

### [Building Insight Engine: How I'm Using GraphRAG to Discover Cross-Domain Innovation (Part 1)](https://sumukha87.hashnode.dev/building-insight-engine-how-i-m-using-graphrag-to-discover-cross-domain-innovation-part-1?utm_source=hashnode&utm_medium=feed)

A deep-dive into building a B2B SaaS knowledge discovery platform — powered by 229K research papers, a knowledge graph, and a single RTX 4060 GPU.

5 min read · [sumukha87.hashnode.dev](https://sumukha87.hashnode.dev/building-insight-engine-how-i-m-using-graphrag-to-discover-cross-domain-innovation-part-1?utm_source=hashnode&utm_medium=feed)

[Mar 23](https://hashnode.com/posts/building-insight-engine-how-i-m-using-graphrag-to-discover-cross-domain-innovation-part-1/69c147aa30a9b81e3a5853a2)
