Software Engineer · Applied AI, GenAI and data · Hyderabad, India

AI and data systems that have to work on real data, not a demo set.

I ship AI and data work to production: classical computer vision that read more than 90,000 paper exam sheets, a data pipeline I cut from 42 minutes to 3.8, and an LLM retrieval chatbot deployed on AWS. Alongside my work at Runo, I'm building deeper in PyTorch and generative AI.

  • Python
  • OpenCV
  • scikit-learn
  • Keras
  • pandas
  • NumPy
  • DuckDB
  • Flask

each page, a thousand sheets90,000+

42 → 3.8 min

Daily call-analytics run

3.8 min now42 min before

~15M / month45M reprocess

Production systems

Selected work

  1. Freelance · Python, OpenCV

    Reading 90,000+ paper exam sheets with computer vision

    Exam answer sheets came in as scans with skew, noise and stray marks. I built a staged Python and OpenCV pipeline that normalizes, aligns and reads each sheet, and recovers a failed stage without rerunning the whole batch.

    Python / OpenCV / Optical Mark Recognition / Image Processing90,000+ sheetsSee the project
  2. Runo · Python, DuckDB

    A daily analytics pipeline, 42 minutes down to 3.8

    The daily call-analytics run recomputed everything from scratch. I rebuilt it as an incremental DuckDB pipeline that skips files it has already processed.

    42 min → 3.8 min
  3. Open source · Python, LlamaIndex, AWS

    An LLM that answers from your documents

    A retrieval-augmented chatbot over a company's documentation, deployed on AWS Lightsail: documents are embedded, the closest chunks are retrieved, and the LLM answers only from that context. The write-up covers scaling from one shared index to per-user indexes.

    Python / Flask / llama_index / RAGSee the project

More work

All work, grouped by area

Experience

  1. Jun 2025 – Present

    Software Engineer, Runo

    On a sales CRM, I take the problems that cut across the product and make them dependable: rep chats that never reached the CRM, analytics nobody could trust, calling modes an account couldn't combine, and a daily report run that took 42 minutes.

  2. Jan 2024 – May 2025

    Mobile Application Developer, NMOLD (OPC) Private Limited

    Part-time during the last three semesters of my B.Tech: rebuilt NMOLD's inventory system and connected its factory machines to it.

  3. Sep 2022 – Dec 2023

    Campus Software Developer, Panipat Institute of Engineering & Technology

    Paid, part-time during my B.Tech. As the college's only developer I built and ran its exam, feedback, ticketing and bus-tracking systems, and kept them running until I graduated.

Freelance

Client work before and during college, grouped by what I built.

Automation and AI

Blockchain

Products for startups

  • A job portal and equipment marketplace for the construction industry
  • A hospital management system, built with a student team
  • A social platform where students track and share achievements
  • The frontend website for a milk-delivery startup

Sites and portals

  • An exam module in Laravel for a civil-services coaching institute
  • A quiz portal for intern certification, and updates to the company website
  • Upkeep of a legacy CodeIgniter property listing site, and a Node.js information portal
  • Fixes and improvements to a company website

Mobile apps

Hosting and operations

  • Plesk servers, DNS and security, including honeypots, across a web agency's hosting
  • Hosting for a news website, including its move to AWS Lightsail
  • Recovering client sites from backups, then hosting, DNS and email

Education

  • B.Tech, Information Technology (AI & Data Science specialization)

    Panipat Institute of Engineering & Technology · 2021–2025

  • Data Science Training Program

    Infosys Springboard · online training · 2024–2025

Day to day: Python, LlamaIndex, RAG, OpenCV, scikit-learn, Keras, pandas, NumPy, DuckDB, Flask, SQL, AWS.

Full résumé

Contact

I'm looking for applied AI, ML and data engineering roles where shipping to production matters. Email is the fastest way to reach me.