Hi, I'm Anish 👋
AI & Full-Stack Engineer specializing in scalable systems, real-time applications, and intelligent software.
AK

About

Final-year Information Technology student with under a year of professional experience and a strong track record in hackathons and rapid prototyping. I build AI-powered and full-stack applications, including real-time systems and scalable web platforms using FastAPI, Next.js, and TypeScript. Passionate about solving real-world problems through efficient system design and practical AI implementation.

Skills

TypeScript
JavaScript
Python
Next.js
React
Node.js
FastAPI
MongoDB
PostgreSQL
WebSockets
Docker
CI/CD
RAG
LLMs
Vector Search
Machine Learning
My Projects

Check out my latest work

I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.

Quickserve

QuickServe is an AI-powered, voice-first ordering system for restaurant workflows. It combines speech recognition, NLU intent/entity parsing, response generation, cart/session persistence, and payment flow support in one stack.

Python
FastAPI
Next.js
Typescript
MongoDB
Rasa NLU
LLMs
TTS & STT

Victor

A production-ready Retrieval-Augmented Generation (RAG) system built with LangChain, featuring intelligent document processing, semantic search, and conversational AI capabilities. The system integrates Google Drive synchronization, web scraping, and multi-modal document processing with enterprise-grade authentication and monitoring.

Next.js
Typescript
MongoDB
Python
FastAPI
LangChain
Vector Search
RAG Pipeline

PCOS Detect

PCOS Detect is an end-to-end AI-powered clinical decision support system designed to assess Polycystic Ovary Syndrome (PCOS)

Next.js
Typescript
SQLite
Python
FastAPI
JWT Authentication
Machine Learning

Devpress

DevPress is a modern, full-stack blogging application built to demonstrate a clean, type-safe, and scalable architecture.It allows users to create, read, edit, and delete blog posts, manage categories, upload images, and search for content - all through a seamless and responsive interface.

Next.js
Typescript
PostgreSQL
Monorepo Architecture
tRPC
Drizzle ORM
Tiptap Editor
Zod Validation

Attendix

ATTENDIX is an AI-powered smart attendance and biometric identity verification system built as part of the HackCrypt 2026 Hackathon. It combines facial recognition and fingerprint verification to provide a secure, contactless, and efficient way to verify student and faculty presence in educational institutions.

Next.js
Typescript
PostgreSQL
Clerk Authentication
Drizzle ORM
Python
FastAPI
OpenCV
Pinecone
Hackathons

I like building things

During my university years, I participated in over five hackathons where driven individuals from across the country came together to build impactful solutions in just a couple of days. Being surrounded by that level of energy and creativity reshaped how I think about collaboration and what can be achieved under tight timelines.

  • P

    Prakalp (2nd Prize) - Quickserve

    Mumbai, India

    Presented Quickserve at Prakalp, an inter-college level competition in organized by Computer department St. Francis Institute of Technology, and secured 2nd prize among 50+ teams for our innovative AI-powered voice-first ordering system designed to revolutionize restaurant workflows.
  • C

    Colloquium (3rd Prize) - Quickserve

    Mumbai, India

    Presented Quickserve at Colloquium, a college level competition in organized by Information Technology department St. Francis Institute of Technology, and secured 3rd prize among 100+ teams for our innovative AI-powered voice-first ordering system designed to revolutionize restaurant workflows.
  • H

    Hackrypt - Cosmic Cypher (3rd Runner up)

    Mumbai, India

    Developed a modern, AI-powered biometric attendance and identity verification platform built for educational institutions combining facial recognition with fingerprint verification to provide a secure, contactless, and efficient way to verify student and faculty presence.
  • C

    Crakathon (IIT Bombay) - (4th place)

    Mumbai, India

    Developed an object detection model to identify and classify road damage using the RDD2022 dataset. The approach leveraged YOLO-based architectures, explored suitable backbones and domain-specific data augmentations, and incorporated ensembling strategies to improve performance.
  • S

    Smart India Hackathon (Finalists) - Victor

    Rourkela, India

    Developed a production-ready Retrieval-Augmented Generation (RAG) system for Ministry of Education, India, performing efficient RAG over a large corpus of educational documents
Contact

Get in Touch

Want to chat? Just shoot me a dm with a direct question on gmail and I'll respond whenever I can. I will ignore all soliciting.