I build full-stackAI products withagentic systems,scalable backends,& polished interfaces.

Experience

Obvix Labs, Remote

2026

Product Designer & Full Stack Developer Intern

Achievements

Top 10 Finalist Nationwide

2025

iMobilothon 5.0 · Volkswagen Group

170+ Day GitHub Streak

Ongoing

GitHub

Academics

B.Tech CSE, Punjab

2023–26

Lovely Professional University · CGPA 8.04

Intermediate, West Bengal

2021–23

Gangarampur High School

Matriculation, West Bengal

2020–21

Gangarampur High School

Selected Work

Projects & Case Studies

A collection of product design work spanning conversational AI, healthcare, and enterprise design systems.

03 Projects

Amyy AI

Architected Amyy AI — a privacy-first AI companion serving 300+ users with v2 backend, OAuth, rate limiting, and LLM workflows shipped end-to-end.

Amyy AI is a privacy-first AI companion framework serving 300+ real-world users. I architected the v2 backend infrastructure — designing the service layer, data models, and API contracts — and built the major frontend, integrating FastAPI services with the client and shipping with Claude Code for fast delivery.

FastAPINext.jsPostgreSQL

View case study→

Nexera

Built Nexera — an autonomous AI research workspace that plans queries, gathers evidence across the web, and ships citation-backed reports with live streaming progress.

Nexera is an autonomous AI research workspace that classifies queries, plans sub-questions, executes searches, fetches and chunks web content, reranks evidence, and synthesizes citation-backed reports — all while streaming progress live. It supports quick, standard, and deep research modes, thread-aware follow-ups, URL/file ingestion, and multimodal capabilities (speech transcription, TTS, image analysis).

Next.jsTypeScriptFastAPI

View case study→

Mentora

Built Mentora — an agentic AI career coach platform with six specialized agents, a three-tier memory system, and a RAG pipeline keeping per-session cost at ~$0.02.

Mentora is an agentic AI career coach platform powered by a six-agent system — diagnostic, planner, accountability, mock interview, escalation, and memory — running on Groq LLMs. I designed a three-tier memory layer with resume/document chunking and embeddings in PostgreSQL + pgvector, Redis episodic caching, and request-scoped working memory, plus a RAG pipeline that powers natural-language admin queries and voice mock interviews.

Next.jsTypeScriptGroq

View case study→

About

Building AI-native products end-to-end — backends, LLM workflows, and polished frontends.

I'm Pinak Kundu, a Product Designer & Full Stack Developer focused on shipping AI/SaaS products from idea to production.

I work across the stack — FastAPI, Node.js, and PostgreSQL on the backend; Next.js and React on the frontend — with hands-on experience in hybrid RAG, multi-agent systems, pgvector, OAuth, rate limiting, Redis caching, and CI/CD on AWS Amplify and Vercel.

I care about products that are useful, fast, and trustworthy. Whether it's a privacy-first AI companion, an autonomous research workspace, or an agentic AI career coach, I focus on shipping real systems that users can rely on.

Currently

Product Designer & Full Stack Developer Intern · Obvix Labs

Focus

AI Products · Full Stack · Agentic Systems

Interests

Hybrid RAG, Multi-Agent Systems, Scalable Backends, Product Design

Download Resume

Skills & Tooling

The stack I reach for.

Languages

C++

Java

Python

JavaScript

Backend

FastAPI

Node.js

Express.js

REST APIs

WebSockets

Frontend

HTML

CSS

React.js

Next.js

Tailwind CSS

Databases, Infra & AI/ML

PostgreSQL

Supabase

Redis

pgvector

Docker

CI/CD

RAG

Multi-Agent Systems

Core CS

DSA

System Design

DBMS

OOP

GitHub

Building in public, every day.

A live snapshot of the last six months on GitHub — commits, pull requests, and the steady cadence behind the work.

@pinakkk

Last 6 months

1,919

contributions

Current streak

187

days

Longest streak

187

days

Best day

Feb 7

Dec 14, 2025 → Jun 18, 2026

LessMore

Dec

Jan

Feb

Mar

Apr

May

Jun

Mon

Wed

Fri

Blog

Thoughts & Writing

Writing on product thinking, frontend architecture, and the systems work behind interfaces that feel clear, calm, and intentional.

02 Articles

Featured Note

Designing Amy AI: turning a non-sycophantic backend into a calm teen-facing product

What it took to design the full UI/UX for Amy AI and integrate it with a FastAPI backend built around anti-sycophancy, model routing, and privacy-first system design.

AI ProductFastAPIUXOpenRouter

Published

Jan 20, 2026

Reading time

3 min read

Read article→

Apr 12, 20263 min

Building Mentora: a six-agent AI career coach with a three-tier memory layer

How I built Mentora — an agentic AI career coach platform — with six specialized agents on Groq, pgvector long-term memory, Redis episodic state, and a RAG pipeline keeping per-session cost at ~$0.02.

Agentic AIMulti-Agent SystemsRAGpgvectorGroq

Open article→

Contact

Let's build something together.

Whether you have a project in mind, want to collaborate on open source, or just want to say hello — I'd love to hear from you.

bypinakkundu@gmail.com

linkedin.com/in/pinakk

GitHub

github.com/pinakkk

Location

Punjab, India

Send a message

“The best code is the code that makes the user forget they're using software.”