What does Amar Tripathi specialize in as a Full Stack Developer & AI Engineer?

Amar Tripathi is a Full Stack Developer and AI Engineer who specializes in building production AI-powered applications using the MERN stack (MongoDB, Express.js, React, Node.js), Next.js, and TypeScript. His AI expertise includes RAG (Retrieval Augmented Generation) pipelines, AI chatbot development, LLM integrations via OpenRouter, and generative AI tools for image, audio, and video generation. He currently works as an SDE at Galaxy AI, building AI productivity tools.

What AI and LLM technologies does Amar Tripathi work with?

Amar works with LangChain for LLM orchestration, OpenRouter for multi-model LLM routing across OpenAI, Anthropic, and Mistral models, vector databases for RAG pipelines, Vercel AI SDK for streaming AI responses, and OpenAI APIs for GPT integrations. He builds full stack AI applications combining these tools with Next.js, TypeScript, React, Node.js, and MongoDB.

Is Amar Tripathi available for hire as a Full Stack AI Developer?

Yes, Amar Tripathi is currently open to full-time roles and freelance projects as a Full Stack Developer and AI Engineer. He is based in India and works remotely. He has professional experience at Galaxy AI (Cambridge, MA) building production AI tools, and at Roboto Studio (London, UK) and GCT Pvt Ltd (Delhi, India). Contact him at theamartripathi@gmail.com.

What is Amar Tripathi's experience with RAG pipelines and AI chatbots?

Amar Tripathi builds RAG (Retrieval Augmented Generation) pipelines that combine document retrieval from vector databases with LLM generation for accurate, context-aware AI responses. His approach uses LangChain for orchestration, vector embeddings for semantic search, and Next.js API routes for serving AI responses with real-time streaming. At Galaxy AI, he builds AI tools that process image, audio, and video generation at scale.

Open to Work!

Resume

Amar

Tripathi

Full-Stack Software Engineer

, building AI products at production scale.

Next.js · TypeScript · Agentic AI Chat · RAG Pipelines · Applied AI

About

Full-stack Software Engineer with 1.5+ years of experience building AI-powered products at production scale. Currently an SDE-1 at Galaxy AI, where I led the development of chat.galaxy.ai — a multi-model agentic AI chat platform supporting 100+ LLMs, processing 1.4 Billion+ tokens/day, ranked #2 in General Chat and #37 globally on OpenRouter.

I specialize in real-time streaming, RAG pipelines, and LLM integration. Key highlights include a 36% TTFB reduction across millions of records and building 60+ AI tools for video, image, and audio generation.

GitHub

@amartripathi0

SDE-1 at Galaxy AI

Delhi, India (Remote)

B.Tech — Computer Science Engineering

BIT Durg · CPI 8.36 / 10 · 2021 – 2025

Open to Work!

Resume

Amar

Tripathi

Full-Stack Software Engineer

, building AI products at production scale.

Next.js · TypeScript · Agentic AI Chat · RAG Pipelines · Applied AI

About

GitHub

@amartripathi0

SDE-1 at Galaxy AI

Delhi, India (Remote)

B.Tech — Computer Science Engineering

BIT Durg · CPI 8.36 / 10 · 2021 – 2025

Experience

Jun 2025 — Present

Galaxy AI

Software Development Engineer 1

Delhi, India

Fulltime

Remote

Led development of chat.galaxy.ai — a multi-model agentic AI chat platform supporting 100+ LLMs, processing 1.4 Billion+ tokens/day. Ranked #2 General Chat and #37 globally on OpenRouter
Architected the full-stack system from the ground up — backend infrastructure, real-time streaming via SSE, multi-tool calling, memory persistence, and the complete frontend in Next.js and TypeScript
Built RAG pipelines for large document processing, enabling contextual AI responses across multi-turn conversations with persistent memory
Reduced Time to First Byte (TTFB) by 36% through async job offloading and request flow optimization; improved database query performance across millions of records via strategic indexing and query tuning
Implemented virtualized rendering (React Virtuoso) to handle large-scale chat histories, reducing DOM node count by 90%+ and eliminating UI crashes in long conversations

Jan 2025 — May 2025

Galaxy AI

Software Developer Intern

Delhi, India

Intern

Remote

Integrated 40+ AI video generation tools by designing scalable video configuration pipelines and enabling parallel processing via webhook workflows using various Gen AI providers for video.galaxy.ai
Engineered 20+ AI-powered media generation tools (video, image, audio) with reusable architecture for rapid feature deployment across multiple product lines

Jun 2024 — Aug 2024

Roboto Studio

Web Developer

Nottingham, UK

Intern

Remote

Delivered responsive websites with 95%+ Lighthouse scores by translating Figma designs into reusable Next.js components; integrated Sanity CMS for scalable content updates
Collaborated with a distributed team across the UK and India using agile workflows via Slack and Linear

May 2024 — Jun 2024

GCT Technologies Pvt Ltd

Fullstack Developer

Delhi, India

Intern

Remote

Replaced REST APIs with GraphQL queries using Apollo, reducing data over-fetching by ~40%
Built frontend features in Next.js, React Native (Expo), and Tamagui in a monorepo architecture

Projects

Featured Project

SDE-1 — Sole Developer

chat.galaxy.ai
atGalaxy AI

Multi-model agentic AI chat platform supporting 100+ LLMs across 12+ providers, processing 1.4B+ tokens/day. Ranked #2 General Chat and #37 globally on OpenRouter.

See it live ↗

Led the development of chat.galaxy.ai as the sole developer — a production-grade, multi-model agentic AI chat platform comparable to ChatGPT. The platform supports 100+ large language models from 12+ providers including OpenAI, Anthropic, Google, xAI, Meta, Deepseek, and Mistral, with seamless cross-model switching mid-conversation.

Built the entire system from the ground up — from backend infrastructure with real-time streaming via Server-Sent Events, to the complete Next.js frontend. The platform handles 1.4B+ tokens daily and is ranked #2 in General Chat and #37 globally on OpenRouter.

Engineered advanced AI capabilities including a multi-tool calling pipeline, RAG pipelines for large document processing, sandboxed code execution across 6 languages, image generation with 3 models, and full voice support — Speech-to-Text, Text-to-Speech, and real-time Voice-to-Voice AI conversations.

The platform features an AI Arena for side-by-side model comparison, custom AI Assistants (GPTs) with uploadable knowledge bases, project-based organization with scoped memory, and workspace settings for personalized chat flows. Optimized performance with 36% TTFB reduction through async job offloading and virtualized rendering to handle massive chat histories without UI crashes.

100+

AI Models

12+ providers

1.4B+

Tokens/Day

processed daily

General Chat

on OpenRouter

#37

Global Rank

on OpenRouter

~2s

Response Time

first token

36%

TTFB Reduced

via async optimization

Verified rankings on OpenRouter

💬

Chat

ChatGPT-like interface with 100+ models

⚔️

AI Arena

Compare 2-4 models side-by-side

🤖

Assistants

Custom GPTs with RAG knowledge base

📁

Projects

Organized chats with scoped files & memory

💬

Chat & Models

Cross-model switching (OpenAI, Anthropic, Google, xAI, Meta, Deepseek, Mistral & more)
Real-time streaming via SSE
Multi-tool calling pipeline
Chat forking & branching
Export — Markdown, JSON, CSV, Screenshot

🎨

Multimodal AI

40+ file format uploads with OCR & extraction
Image generation — 3 models, text-to-image & image-to-image
Speech-to-Text & Text-to-Speech
Voice-to-Voice real-time AI chat

🧠

Knowledge & Memory

RAG pipelines for large document processing
Persistent AI memory across conversations
Project-scoped files, instructions & memory
Workspace settings to customize chat flow

⚡

Developer Tools

Sandboxed code execution — Python, JS, TS, Java, R, Bash
Web Search & Web Fetch with citations
AI Arena — compare 2-4 models side-by-side
Custom AI Assistants (GPTs) with RAG knowledge base

Full-stack system architected from the ground up

Real-time streaming via Server-Sent Events (SSE)

36% TTFB reduction through async job offloading

DB optimization across millions of records via strategic indexing

Virtualized rendering (React Virtuoso) — 90%+ DOM reduction

Background workers for long-running tasks

RAG pipelines enabling contextual multi-turn conversations

Memory persistence across conversations

Next.js

TypeScript

Tailwind CSS

SSE Streaming

React Virtuoso

RAG Pipelines

Background Workers

Blogs and Blogs

Simple Blogging Site - Discover insightful articles, expert opinions, and cutting-edge ideas from industry leaders.

React TS Vite

Hono.js Server

Prisma

Cloudflare Workers

Postgres DB

Zod

Tailwind

Framer Motion

Source Code See it live ↗

Placement Nexus

Placement Nexus is an ongoing MERN stack-based project streamlining university hiring. It connects students, recruiters, and colleges for efficient recruitment. Stay tuned for major frontendand backend enhancements.

React JS

React Hook Form

React Router DOM

Redux Toolkit

Axios

React Toastify

Tailwind CSS

Node JS

...

Source Code See it live ↗

YT Playlist Analyzer

Analyze the time required to watch a youtube playlist in various available speeds such as 1x, 1.25x , 1.5x, 1.75x and 2x. It simplifies playlist consumption by calculating the total duration of videos within a given YouTube playlist.

Nextjs/React

Typescript

Tailwind CSS

React Hook Form

Axios

Sonner

Google YouTube API

Vercel

Source Code See it live ↗

Freelance Work

Ready to elevate your online presence? Let's create something exceptional together!

HIRE ME — and Get It Done!

Dr. Gajanan Shirke Portfolio

See it live ↗

Swastik Construction

See it live ↗

AI & Development Stack

AI & LLM

AI Agent Architecture

Multi-LLM Orchestration

Prompt Engineering

RAG Pipelines

Hybrid Search

Embeddings & Vector DBs

LLM Tool Calling

Sandboxed Code Execution

Vision & Image Gen

Text-to-Speech & STT

Real-time Voice Chat

Context Window Mgmt

Long-term AI Memory

AI Agent Architecture

Multi-LLM Orchestration

Prompt Engineering

RAG Pipelines

Hybrid Search

Embeddings & Vector DBs

LLM Tool Calling

Sandboxed Code Execution

Vision & Image Gen

Text-to-Speech & STT

Real-time Voice Chat

Context Window Mgmt

Long-term AI Memory

AI Web Search

Document Processing & OCR

Real-time Streaming

AI Safety & Guardrails

LLM Evaluation

Background AI Pipelines

OpenAI API

Claude API

OpenRouter

Vercel AI SDK

LangChain

Pinecone

AI Web Search

Document Processing & OCR

Real-time Streaming

AI Safety & Guardrails

LLM Evaluation

Background AI Pipelines

OpenAI API

Claude API

OpenRouter

Vercel AI SDK

LangChain

Pinecone

Frontend

React JS

Next JS

TypeScript

JavaScript

Tailwind CSS

Redux Toolkit

Zustand

Framer Motion

HTML

CSS

Backend & Infra

Node JS

Express JS

Python

MongoDB

PostgreSQL

Prisma

GraphQL

Java

SQL

AWS

Git

GitHub Actions

Vercel

Postman

Let's Talk

Designed & Developed by Amar Tripathi

theamartripathi@gmail.com

Experience

Jun 2025 — Present

Galaxy AI

Software Development Engineer 1

Delhi, India

Fulltime

Remote

Led development of chat.galaxy.ai — a multi-model agentic AI chat platform supporting 100+ LLMs, processing 1.4 Billion+ tokens/day. Ranked #2 General Chat and #37 globally on OpenRouter
Architected the full-stack system from the ground up — backend infrastructure, real-time streaming via SSE, multi-tool calling, memory persistence, and the complete frontend in Next.js and TypeScript
Built RAG pipelines for large document processing, enabling contextual AI responses across multi-turn conversations with persistent memory
Reduced Time to First Byte (TTFB) by 36% through async job offloading and request flow optimization; improved database query performance across millions of records via strategic indexing and query tuning
Implemented virtualized rendering (React Virtuoso) to handle large-scale chat histories, reducing DOM node count by 90%+ and eliminating UI crashes in long conversations

Jan 2025 — May 2025

Galaxy AI

Software Developer Intern

Delhi, India

Intern

Remote

Integrated 40+ AI video generation tools by designing scalable video configuration pipelines and enabling parallel processing via webhook workflows using various Gen AI providers for video.galaxy.ai
Engineered 20+ AI-powered media generation tools (video, image, audio) with reusable architecture for rapid feature deployment across multiple product lines

Jun 2024 — Aug 2024

Roboto Studio

Web Developer

Nottingham, UK

Intern

Remote

Delivered responsive websites with 95%+ Lighthouse scores by translating Figma designs into reusable Next.js components; integrated Sanity CMS for scalable content updates
Collaborated with a distributed team across the UK and India using agile workflows via Slack and Linear

May 2024 — Jun 2024

GCT Technologies Pvt Ltd

Fullstack Developer

Delhi, India

Intern

Remote

Replaced REST APIs with GraphQL queries using Apollo, reducing data over-fetching by ~40%
Built frontend features in Next.js, React Native (Expo), and Tamagui in a monorepo architecture

Projects

Featured Project

SDE-1 — Sole Developer

chat.galaxy.ai
atGalaxy AI

Multi-model agentic AI chat platform supporting 100+ LLMs across 12+ providers, processing 1.4B+ tokens/day. Ranked #2 General Chat and #37 globally on OpenRouter.

See it live ↗

100+

AI Models

12+ providers

1.4B+

Tokens/Day

processed daily

General Chat

on OpenRouter

#37

Global Rank

on OpenRouter

~2s

Response Time

first token

36%

TTFB Reduced

via async optimization

Verified rankings on OpenRouter

💬

Chat

ChatGPT-like interface with 100+ models

⚔️

AI Arena

Compare 2-4 models side-by-side

🤖

Assistants

Custom GPTs with RAG knowledge base

📁

Projects

Organized chats with scoped files & memory

💬

Chat & Models

Cross-model switching (OpenAI, Anthropic, Google, xAI, Meta, Deepseek, Mistral & more)
Real-time streaming via SSE
Multi-tool calling pipeline
Chat forking & branching
Export — Markdown, JSON, CSV, Screenshot

🎨

Multimodal AI

40+ file format uploads with OCR & extraction
Image generation — 3 models, text-to-image & image-to-image
Speech-to-Text & Text-to-Speech
Voice-to-Voice real-time AI chat

🧠

Knowledge & Memory

RAG pipelines for large document processing
Persistent AI memory across conversations
Project-scoped files, instructions & memory
Workspace settings to customize chat flow

⚡

Developer Tools

Sandboxed code execution — Python, JS, TS, Java, R, Bash
Web Search & Web Fetch with citations
AI Arena — compare 2-4 models side-by-side
Custom AI Assistants (GPTs) with RAG knowledge base

Full-stack system architected from the ground up

Real-time streaming via Server-Sent Events (SSE)

36% TTFB reduction through async job offloading

DB optimization across millions of records via strategic indexing

Virtualized rendering (React Virtuoso) — 90%+ DOM reduction

Background workers for long-running tasks

RAG pipelines enabling contextual multi-turn conversations

Memory persistence across conversations

Next.js

TypeScript

Tailwind CSS

SSE Streaming

React Virtuoso

RAG Pipelines

Background Workers

Blogs and Blogs

Simple Blogging Site - Discover insightful articles, expert opinions, and cutting-edge ideas from industry leaders.

React TS Vite

Hono.js Server

Prisma

Cloudflare Workers

Postgres DB

Zod

Tailwind

Framer Motion

Source Code See it live ↗

Placement Nexus

React JS

React Hook Form

React Router DOM

Redux Toolkit

Axios

React Toastify

Tailwind CSS

Node JS

...

Source Code See it live ↗

YT Playlist Analyzer

Nextjs/React

Typescript

Tailwind CSS

React Hook Form

Axios

Sonner

Google YouTube API

Vercel

Source Code See it live ↗

Amar

Tripathi

About

GitHub

Amar

Tripathi

About

GitHub

Experience

Galaxy AI

Software Development Engineer 1

Galaxy AI

Software Developer Intern

Roboto Studio

Web Developer

GCT Technologies Pvt Ltd

Fullstack Developer

Projects

chat.galaxy.aiatGalaxy AI

Chat & Models

Multimodal AI

Knowledge & Memory

Developer Tools

Blogs and Blogs

Placement Nexus

YT Playlist Analyzer

Freelance Work

AI & Development Stack

AI & LLM

Frontend

Backend & Infra

Let's Talk

Experience

Galaxy AI

Software Development Engineer 1

Galaxy AI

Software Developer Intern

Roboto Studio

Web Developer

GCT Technologies Pvt Ltd

Fullstack Developer

Projects

chat.galaxy.aiatGalaxy AI

Chat & Models

Multimodal AI

Knowledge & Memory

Developer Tools

Blogs and Blogs

Placement Nexus

YT Playlist Analyzer

Freelance Work

AI & Development Stack

AI & LLM

Frontend

Backend & Infra

Let's Talk

chat.galaxy.ai
atGalaxy AI

chat.galaxy.ai
atGalaxy AI