Harsh Upadhyay

Software Engineer

I design and build full-stack & AI-driven systems — from database schema to the interface a user actually touches.

Resume

01. About

Hi, I'm Harsh — a software engineer who likes turning gnarly technical problems into things that actually ship. I'm finishing my B.Tech in Information Technology at Manipal University Jaipur, and I spend most of my time building full-stack and AI-driven systems end to end.

Right now I'm co-founding zero2one labs, a small studio building custom websites for local businesses, alongside production-grade side projects like Codenaut, an AI codebase-intelligence platform, and Anteroom, a live voice-based AI interview coach.

I care about the unglamorous parts too — test coverage, migrations, auth, and the debugging war stories nobody sees.

Languages

Java, Python, JavaScript, SQL

Frontend

React, TypeScript, Vite, Tailwind CSS

Backend

FastAPI, Node.js, Express, REST APIs, WebSockets

Data & AI

PostgreSQL, MongoDB, Redis, RAG, Vector Search, Prompt Engineering

180+ problems solved on LeetCode.

02. Experience

Co-Founder & Full-Stack Developer · zero2one labs

2026 — Present

  • Co-founded a web development studio building custom, mobile-first websites for small businesses across Jaipur & Hyderabad; shipped 9 client projects end to end.
  • Built responsive React / Tailwind frontends and FastAPI backends, selecting MySQL, PostgreSQL, or MongoDB per client's needs.
  • Owned the full client lifecycle — requirement gathering, live demos, iteration on feedback, deployment, and post-launch support.
  • Sourced and qualified leads through targeted local outreach, managing the process from cold contact through to signed client.

AI & Machine Learning Intern · Infosys Springboard

Nov 2025 — Jan 2026

  • Built a CNN-based emotion detection model in Python and TensorFlow on the FER-2013 dataset, covering preprocessing, training, and evaluation.
  • Applied structured, iterative debugging to diagnose accuracy issues and improve model performance.

03. Projects

Codenaut Flagship

AI-Powered Codebase Intelligence SaaS

A multi-tenant SaaS that securely indexes GitHub repositories and answers natural-language questions about unfamiliar codebases — grounded in exact files, symbols, and commits, not hallucinated.

  • FastAPI backend with async SQLAlchemy 2.x + PostgreSQL, and a Redis Streams-based durable job queue with retry and recovery.
  • Tree-sitter static analysis extracts symbols and a conservative call graph without executing repository code.
  • A bounded AI agent (3 read-only tools, max 4 calls) validates every citation against server-collected evidence to prevent hallucination.
  • 332 backend tests at 91% branch coverage; strict mypy & Ruff clean; Dockerized CI with vulnerability scanning.
  • Python
  • FastAPI
  • PostgreSQL
  • Redis
  • Tree-sitter
  • Qdrant
  • React
  • TypeScript

Anteroom

Live Voice-Based AI Interview Coach

A production-deployed, full-stack app that runs real-time voice mock interviews — transcribing, evaluating, and scoring answers turn by turn as you speak.

  • Real-time WebSocket state machine: speech-to-text → adaptive LLM question generation → 4-dimension answer evaluation → text-to-speech.
  • Resume-aware personalization parses uploaded PDFs/DOCX into a candidate profile that drives question generation.
  • Fine-tuned a Qwen2.5-1.5B evaluator (LoRA via Apple MLX) through knowledge distillation, cutting average scoring error from ~5.3–7.4 points to 0.6–1.9 on a 0–10 scale.
  • Diagnosed and fixed real production incidents — an OOM crash from an eagerly-loaded local model, a WebSocket idle-timeout behind a reverse proxy, and cross-site cookie issues.
  • Python
  • FastAPI
  • WebSockets
  • PostgreSQL
  • Groq
  • React
  • Tailwind
  • MLX

Visitor Management System

Enterprise Full-Stack Application

A deployed visitor management system with real-time notifications and automated reporting for multi-location organizations.

  • 10+ REST endpoints for visitor check-in/out, approvals, and admin workflows on Node.js/Express with MongoDB.
  • Push notifications to admins on new check-ins via Firebase Cloud Messaging.
  • Automated daily Excel exports via a scheduled cron job, plus photo capture/upload via Cloudinary.
  • Diagnosed and resolved data-integrity issues across concurrent registrations and approvals.
  • React
  • Node.js
  • Express
  • MongoDB
  • JWT
  • RBAC
  • Docker

04. Education

Education

B.Tech, Information Technology

Manipal University Jaipur · 2022 — 2026

CGPA: 7.29

Certifications

OCI 2025 Certified AI Foundations Associate

OCI 2025 Certified Foundations Associate

Oracle Data Platform 2025 Certified Foundations Associate

Oracle University · issued Jun 2026

05. Contact

I'm always open to interesting problems, internships, and full-time roles. My inbox is the fastest way to reach me — I'll get back to you.

Say Hello