Ankit Dey

Engineer · Polymath ·

hey, i’m ankit, a computer engineering student who started coding because in 9th grade i realised a few lines of text could make things work my way.

Book a call

Location

Kolkata, India

Building

Cool stuff. Always.

Focus

AI Systems & Web Scale

about

//

A backend dev and AI/ML engineer who loves building stuff that actually works at scale. I've shipped Discord bots like that hit 200k+ users, and built that use computer vision and GenAI to make sense of messy, real-world data. I spend most of my time making things fast, reliable, and actually useful, not just technically impressive.

Current Focus

Building with LLMs & RAG

Philosophy

Make it work, then make it fast

Status

Down to collaborate

Expertise

Web Systems, AI Agents

education

Narula Institute of Technology

Python
C++
DSA
Operating System
NLP
LLMs
Neural Networks
Distributed Systems

Oriental Public School

Python
MySQL
Algorithms

St Joseph's School

HTML
CSS
JavaScript
Java

work experience

Independent OSS & Freelance

Enhanced ML inference pipelines with Python and FastAPI, processing 50k+ daily requests with 40% lower latency and 60% higher throughput. Improved semantic search relevance by 25% via KMeans clustering and vector database indexing.
Built RAG systems with LangChain and ChromaDB, reducing hallucination rates by 15% through prompt engineering and retrieval tuning while maintaining 90%+ accuracy across multi-agent workflows.
Implemented production-grade MCP client with OAuth 2.1 + PKCE authentication, SHA-256 code challenges, and ephemeral state tokens for CSRF protection. Managed cryptographically secure verifiers across asynchronous interaction lifecycles, enabling authenticated access to Swiggy Instamart's tool catalog via the official MCP SDK.

Python
FastAPI
LangChain
ChromaDB
RAG
MCP
OAuth 2.1
Vector DB

Sync Music

Node.js
Discord.js
TypeScript
Scaling
Monetization

achievements

16

2022

The Spark & First Lines of Code

Scored 84% in ICSE 10th standard, but what truly reshaped everything was writing my first lines of Python and querying MySQL. It was the moment code stopped being an abstract subject and became a tool to build logic from scratch.

17

2023

Scaling Sync Music

Dived into TypeScript, Node.js, and Discord.js to solve low-latency audio streaming. That experiment turned into Sync Music, scaling to over 200k users and 2k servers, earning official Discord Verification, and generating recurring revenue as documented in my announcement.

18

2024

Secondary School & CS Focus

Completed 12th CBSE in PCM and Computer Science, scoring 93 in Computer Applications. Proving to myself that strong theoretical fundamentals directly fuel better engineering, setting the stage for full-time computer engineering.

19

2025

College, SIH Finalist & Computer Vision

Joined Narula Institute of Technology for B.Tech in CSE. Pushed into my first hackathon at Smart India Hackathon and advanced all the way to the national final round, while engineering a real-time student attention tracking system powered by OpenCV, 468-point MediaPipe face landmarks, and Eye Aspect Ratio scoring.

20

2026

Member of Swiggy Builders Club

Selected for the exclusive Swiggy Builders Club after crafting Swiggy MCP inside Discord, a Model Context Protocol integration backed by OAuth 2.1 PKCE verification, SHA-256 state hashing, and automated token lifecycle management.

work

Count: 04

200k+ active users

Sync Music

Verified Discord music bot for 200k+ users.

•Live

Scalable Discord.js v14 + TypeScript architecture with a pluggable command/event layer, MongoDB persistence, Lavalink audio streaming, and premium/vote-gated controls.

Discord.jsTypeScriptMongoDBLavalinkNode.js

INDEX

RAG pipeline

TubeInsight AI

Comment intelligence and insight discovery.

•Repo

End-to-end ingestion, preprocessing, embeddings, semantic indexing, KMeans theme discovery, and a RAG chat layer for fast feedback exploration.

EmbeddingsKMeansRAGNLPVectorDBs

94.3% accuracy

landmarks // ear_ratio

E.A.R and Face Landmark Detection

Real-time attention monitoring with CV.

•Live

Python, MediaPipe, and OpenCV system using 468-point facial landmark tracking and Eye Aspect Ratio blink scoring for attention detection.

Computer VisionMediaPipeOpenCVPython

builders club

Swiggy MCP Discord Bot

Builders Club prototype for Swiggy inside Discord.

•Build

Discord.js v14 and TypeScript bot that connects Swiggy Instamart through MCP with OAuth 2.1 PKCE login, secure token lifecycle handling, and slash-command auth flows.

Discord.jsTypeScriptMCPOAuth 2.1Express

200k+ active users

Sync Music

Verified Discord music bot for 200k+ users.

•Live

Scalable Discord.js v14 + TypeScript architecture with a pluggable command/event layer, MongoDB persistence, Lavalink audio streaming, and premium/vote-gated controls.

Discord.jsTypeScriptMongoDBLavalinkNode.js

INDEX

RAG pipeline

TubeInsight AI

Comment intelligence and insight discovery.

•Repo

End-to-end ingestion, preprocessing, embeddings, semantic indexing, KMeans theme discovery, and a RAG chat layer for fast feedback exploration.

EmbeddingsKMeansRAGNLPVectorDBs

94.3% accuracy

landmarks // ear_ratio

E.A.R and Face Landmark Detection

Real-time attention monitoring with CV.

•Live

Python, MediaPipe, and OpenCV system using 468-point facial landmark tracking and Eye Aspect Ratio blink scoring for attention detection.

Computer VisionMediaPipeOpenCVPython

builders club

Swiggy MCP Discord Bot

Builders Club prototype for Swiggy inside Discord.

•Build

Discord.js v14 and TypeScript bot that connects Swiggy Instamart through MCP with OAuth 2.1 PKCE login, secure token lifecycle handling, and slash-command auth flows.

Discord.jsTypeScriptMCPOAuth 2.1Express