# Himanshu Gupta - Full Stack AI Engineer

> Full Stack AI Engineer in Delhi building production AI systems: agent workflows, OCR pipelines and multi-agent RAG. Open to freelance and full-time roles.

- Location: Delhi, India
- Education: B.Tech in AI & Data Science, Maharaja Agrasen Institute of Technology (MAIT), Delhi
- Experience: 8 months
- Availability: Open to freelance AI & full-stack projects, as well as full-time roles
- Website: https://www.himex.tech

## About

B.Tech AI & Data Science student at MAIT, Delhi. Hands-on builder focused on turning AI ideas into real production systems. Built ClipSync (AI video pipeline with Gemini VLM and FFmpeg), AI Medical Scheduling Agent (multi-API conversational workflows), and Math Mentor (multi-agent reasoning with RAG memory). Currently a Full Stack AI Engineer at Sparkonomy. Previously a Python Developer Intern at EspoMedia (Jan–Apr 2026), building OCR pipelines with OpenCV, EasyOCR, and PyTorch, automating data workflows, and improving model accuracy in production. I enjoy owning problems end-to-end—designing APIs, integrating models, debugging edge cases, and shipping systems that people actually use. Especially interested in AI that meets real products through agent workflows, data pipelines, and scalable backend systems.

## Experience

### Full Stack AI Engineer at Sparkonomy (May 2026 - Present)

Technologies: Next.js, TypeScript, React, FastAPI, LangGraph, Google Cloud

### Python Developer Intern at EspoMedia (Jan 2026 - Apr 2026)

Tech Department, worked on OCR pipelines, ML/DL model training, and data automation.

- Assisted in building OCR pipelines using EasyOCR, Tesseract, OpenCV, and preprocessing techniques
- Supported training and fine-tuning ML/DL models using PyTorch/TensorFlow and YOLO via Roboflow
- Wrote Python scripts for data cleaning, automation, and dataset preparation
- Used FFmpeg for video/frame extraction and media processing tasks
- Worked with MongoDB to store and manage OCR/model outputs
- Tested model outputs, documented issues, and helped improve accuracy and performance
- Collaborated with the team, maintained clean code, and followed Git-based workflows

Technologies: Python, OpenCV, EasyOCR, Tesseract, PyTorch, TensorFlow, YOLO, FFmpeg, MongoDB

## Projects

### ClipSync

AI-powered video editing automation system that intelligently merges A-Roll with contextually relevant B-Roll footage through a single API call. Uses Gemini VLM for visual analysis and implements intelligent placement algorithms for optimal narrative flow.

- Tech: Python, Gemini API, FFmpeg, NLP
- Source: https://github.com/himax12/clipsync

### Math Mentor (Freelance · MathPilot)

Autonomous reasoning system designed to solve high-school and undergraduate level mathematics problems with high reliability. Unlike typical chat interfaces, this application decouples semantic understanding from deterministic computation. The system accepts multimodal inputs (text, image, audio) and employs a Human-in-the-Loop (HITL) workflow to handle ambiguity before it propagates to the solver.

- Tech: Python, RAG, Multi-Agent, HITL, Multimodal
- Source: https://github.com/himax12/math-mentor
- Live: https://math-mentor-933543570439.us-central1.run.app/

### AI Medical Scheduling Agent

Autonomous conversational AI agent that streamlines patient booking through natural language. Features LangGraph state management, multi-API orchestration with Groq API (Llama 3 70B), and Calendly integration for intelligent appointment scheduling.

- Tech: Python, LangGraph, FastAPI, Streamlit, Groq API
- Source: https://github.com/himax12/medical-scheduling-agent

## Tech stack

- Frontend: React.js, Next.js, TypeScript, JavaScript, Tailwind CSS
- Backend: Node.js, Express.js, Python, FastAPI
- Database: MongoDB, PostgreSQL, SQLite, Supabase
- Languages: Python, JavaScript, TypeScript, C++, C, SQL
- Tools: Git, GitHub, FFmpeg, Streamlit, Pandas, NumPy
- Ai: TensorFlow, PyTorch, OpenCV, LangGraph, Groq API, Gemini API, NLP

## Open source

Merged pull requests to other projects: https://github.com/pulls?q=author%3Ahimax12%20is%3Amerged%20-user%3Ahimax12

## Links

- [GitHub](https://github.com/himax12)
- [LinkedIn](https://www.linkedin.com/in/himanshu-gupta23/)
- [X / Twitter](https://x.com/ayy_him_anshu23)
- [Codolio coding profile](https://codolio.com/profile/himax12)
- [Resume](https://drive.google.com/file/d/10syKMj3XGvfZqTqDSvEsXBOGLXt1Hter/view?usp=sharing)
- [Book a call](https://calendly.com/ghimansh23/30min)
- Email: ghimax23@gmail.com