Vedang — a notebook, mostly.

The short version · for skimming

Software Engineer

I ship production front ends in Next.js, build REST/GraphQL back ends in Node and FastAPI, automate the data pipelines around them, and lately build RAG systems that answer with citations — and I care whether the thing actually got faster and easier to use.

Stack

TypeScriptPythonJavaGoReactNext.jsNode.jsFastAPIGraphQLPostgreSQLDockerRAG / LLMs

What shipped

— PHP → Next.js migration: 40% faster page loads, 90+ Lighthouse
— Compliance crawler: 10,000+ records/day validated from 50+ live sources
— Regulatory Change Radar: clause-level diffs, answered with citations

résumé (PDF)email the workbench →

Spread · The Workbench

Things I've built, shipped, and occasionally rebuilt.

Personal · 2026 → Now

Regulatory Change Radar

/ In progress · RAG

A system that ingests versioned regulatory and sanctions documents, detects clause-level changes between versions, and answers grounded questions with citations to the exact source — and returns “insufficient context” when retrieval confidence is low. Python, FastAPI, a vector DB, and an LLM, tuned to never bluff. Still actively building.

open the page →

clause-level diffs, cited.

KYC2020 · Nov 2025 → May 2026

Migrating a compliance platform to Next.js

/ SDE Intern

Led the PHP → Next.js migration of the company site, wiring GraphQL alongside the existing REST APIs for leaner data fetching — 40% faster page loads and 90+ Lighthouse. Then built the unglamorous glue around it: Node APIs with caching and retries, and a Java/Selenium/Playwright crawler pulling 10,000+ compliance records a day from 50+ live sources.

open the page →

Migrating a compliance platform to Next.js — screenshot

40% faster, 90+ lighthouse.

Personal · 2025

CRO Opportunity Engine

/ Shipped · LLM

Scrapes live Shopify store data — stock levels, reviews, descriptions — and uses an LLM to identify and rank conversion-optimization opportunities by impact, confidence, and effort. TypeScript, Next.js, OpenRouter, and Cheerio doing the reading.

open the page →

ranked by impact × confidence.

see everything I'm building — the full workbench →

Spread · Experience

A rough timeline of how I got here.

2022

started B.Tech in Electronics & Communication at GGSIPU, New Delhi.where it began

Jul 2024

first internship — ML at CETPA. built a chatbot that hit 89% intent accuracy.my first taste

2025

three roles back to back — frontend at Ideomethod, then CVNT, then SDE.

Nov 2025

SDE Intern at KYC2020: led the PHP → Next.js migration.currently here

2026

graduating; going deeper on RAG, systems, and reverse engineering.

still being written.

A detour, if you'd like one

most ideas start as ugly little drawings before they earn any code.

flows, wireframes, half-arrows, scribbles I'd be embarrassed to show in a meeting. they all live in the sketchbook.

open the collection

the sketchbook.

I like building the surfaces people actually touch — and the systems underneath that make them trustworthy. — front end to retrieval, I like the whole stack.

Things I've built, shipped, and occasionally rebuilt.

Regulatory Change Radar

Migrating a compliance platform to Next.js

CRO Opportunity Engine

A rough timeline of how I got here.

most ideas start as ugly little drawings before they earn any code.

say hello.