Bangalore · open to freelance & contract work

full-stack AI engineer.

I build the kind of software where AI stops being a demo and starts pulling its weight — agentic backends, document pipelines that catch real money, desktop apps your client can actually install. Small teams, ambitious scope; I take it from the first conversation to the packaged build.

/now
Now shipping
Agentic-AI platform @ Accenture (NDA)
Open to
Freelance & contract — AI/full-stack
Thinking about
Agentic SQL, sub-second LLMs, packaged apps
Operating from
Bangalore, IST
0+Resumes parsed by my NLP pipeline
0+Employees served via BARCGPT
0Things on this page I built
Agentic systemsDashboardsDocument AIDesktop appsOAuthQuantized LLMsSQL
Agentic systemsDashboardsDocument AIDesktop appsOAuthQuantized LLMsSQL
01 — About

A quick hello.

I write code that lives close to users and decisions. Most of what I build ends up as a Chrome extension, a desktop app, or a small API on a free VM — specific enough to be useful, small enough that one person can hold the whole shape in their head.

Right now I'm shipping an agentic-AI platform for a Fortune 500 client — answers grounded directly in their operational data, no hallucinated numbers, packaged as a single desktop app. Before that, BARCGPT — an OCR + LLM pipeline that caught ₹2L+ in faulty reimbursement claims by reading scanned bills better than the humans were.

I'm biased toward the pragmatic tool over the popular one. Grounded agents over RAG when the data is structured. Packaged executables when end-users don't have Python. SQLite when Postgres would just be theatre. I demo earlier than feels comfortable, and push back with a working prototype rather than an argument.

Off-hours: I'm probably writing a small browser extension to fix something that annoys me, compressing a WhatsApp file without leaving the chat, or solving Tatkal captchas with OCR because IRCTC refuses to be reasonable. Happy to take on freelance and contract work — get in touch below.

02 — Selected work

Things I've shipped.

03 — Stack

The tools
I reach for.

Python and TypeScript are my daily drivers. Everything else is picked per problem — pragmatic over fashionable.

Python01
TypeScript02
C# / .NET03
FastAPI04
React05
Next.js06
Electron07
SQLAlchemy08
PostgreSQL / SQLite09
PaddleOCR10
PyTorch11
Claude / MCP12
DSPy13
Pandas14
Docker15
Azure16
04 — Trajectory

A short history.

  1. Oct 2025 — Present

    Full-stack AI Engineer Accenture, Bangalore

    Shipping AI-powered internal tools for a Fortune 500 client. Sole developer end-to-end — stakeholder requirements, backend, UI, packaging, demos. Details under NDA.

  2. Jan 2025 — Jun 2025

    AI/ML Research Intern Bhabha Atomic Research Centre (BARC), Mumbai

    Built BARCGPT — an OCR + LLM document-intelligence system for reimbursement claims. Ran a quantized 7B model on 8GB of VRAM and cut inference latency from 10s to 1.5s.

  3. Jun 2024 — Jul 2024

    Data Analyst Intern Bhabha Atomic Research Centre (BARC), Mumbai

    Analyzed 10,000+ housing records under DAE; designed and shipped 8 Grafana dashboards backed by MariaDB for live occupancy and allocation insights.

  4. Aug 2023 — Oct 2023

    AI/ML Intern Telekinetics, Pune

    Built a Python resume-parsing system processing 45,000+ candidates with 95% accuracy via Flask + spaCy. Identified 20+ pre-launch bugs on a voice-authentication app before its global release.

  5. Jun 2023 — Jul 2023

    Infosec Intern Nuclear Power Corporation of India (NPCIL), Mumbai

    Deployed and configured Snort (open-source IDS) to monitor and triage network threats with the incident-response team.

  6. Jul 2021 — Jul 2025

    B.Tech, Computer Science VIT Vellore — CGPA 8.64 / 10

    Selected to Amazon ML Summer School 2024 (3,000 from 60,000+ applicants).

05 — Contact

Let's build
something good.

Best place to reach me is email. I read everything and usually reply within a day or two.