# Sreenitya Thatikunta

> Sreenitya Thatikunta is a Computer Science undergraduate at IIT Jodhpur who builds at the intersection of AI, machine learning and software engineering — diffusion and vision-language models, forecasting pipelines, and full-stack web products.

Canonical HTML: https://www.sreenitya.in/

## About me

Hello, I'm Sreenitya!

I'm a Computer Science undergraduate at IIT Jodhpur who loves building things at the intersection of AI, machine learning, and software engineering. I enjoy taking ideas from “this would be cool” to something people can actually use, and I'm always excited to explore new technologies if they help solve the problem better.

I like creating products that are simple, fast, and thoughtfully designed, with as much attention to the user experience as the code behind it. Whether it's an AI experiment, a web application, or a side project that started out of curiosity, I enjoy building things that are both technically interesting and genuinely fun to use.

Outside of tech, I'm probably watching Formula 1 or cricket, hunting for a good coffee spot, or pretending I'll watch just one episode before inevitably finishing half the season.

## Skills

### Programming Languages

- Python
- C++
- C
- SQL
- JavaScript
- TypeScript
- HTML
- CSS
- Bash/Shell Scripting

### AI & Machine Learning

- PyTorch
- Scikit-Learn
- OpenCV
- Deep Learning
- Transfer Learning
- Time Series Models
- LLMs
- VLMs
- Agentic AI

### Data Science

- NumPy
- Pandas
- Matplotlib
- Plotly
- Optuna

### Web & Back end

- React
- Node.js
- Express
- FastAPI
- MongoDB
- Supabase
- Redis

### Cloud & Data Platforms

- Databricks
- Snowflake

### Developer Tools

- Git
- GitHub
- Linux
- IntelliJ IDEA
- VS Code
- Postman
- Streamlit
- Weights & Biases
- LaTeX

## Experience

### JPMorgan Chase & Co. — Summer Analyst (Jun 2026 - Jul 2026)

- Built production forecasting pipelines using Prophet on 6+ years of banking transaction data.
- Modelled trend, seasonality, holidays, and demand spikes for better capacity planning.
- Delivered 92% forecasting accuracy during Amazon Prime business events.

### Pulsegen Pvt Ltd — Full Stack Developer Intern (May 2025 - Jul 2025)

- Architected an AI-powered field management system with frontend, backend, and database design.
- Integrated Mixpanel and ClickUp APIs to build analytics infrastructure and automated task workflows.
- Built a platform-wide data export pipeline for application data and reporting portability.

## Projects

### Manus

Fine-tuned PixArt-diffusion with LoRA on 3,000+ hand images and LLaVA captions. Reduced FID by 13.5% via Optuna tuning, benchmarked variants with FID and T2I-CompBench, tracked experiments in W&B, and deployed a Gradio demo.

- [github](https://github.com/SreenityaThatikunta/PixArt-Alpha-LoRA)

### Visus

Built a CLIP-guided cross-modal segmentation model for text-conditioned facial occlusion localization. Used synthetic training data, prompt augmentation, and Dice loss optimization to reach 94.4% mIoU on CelebA and 94.1% on LFW.

- [report](https://www.sreenitya.in/Face_Segmentation_Report.pdf)

### Atlas

Built a ResNet-50 image retrieval pipeline for CIFAR-10 with LDA reduction and classifier evaluation. Delivered 91%+ accuracy and deployed the system in Streamlit.

- [github](https://github.com/SreenityaThatikunta/Image-Retrieval)

### Mini projects

- terria: daily geography game — Like Wordle but with places — a daily geography guessing game.
- lumière wallpapers — An Unsplash-backed wallpaper app for Android.
- workout tracker — Built because no app had exactly what I wanted.
- photobooth — Strike a pose, save the moment — a browser photobooth.
- meme search extension — Indexed chaos, searchable — a browser extension for meme search.
- stock market agent — Watches Indian markets so you don't have to.

## Contact

Email sreenityathatikunta@gmail.com, or use the contact form on the homepage.

- [LinkedIn](https://www.linkedin.com/in/sreenitya-thatikunta-b16a8a287/)
- [GitHub](https://github.com/SreenityaThatikunta)
- [Resume (PDF)](https://www.sreenitya.in/SreenityaT_Resume.pdf)
- [Contact page](https://www.sreenitya.in/contact)

## For AI agents and developers

This site publishes a read-only JSON API, an OpenAPI 3.0.3 specification, markdown variants of every page and an llms.txt index, so agents do not have to scrape the interface.

- [API documentation](https://www.sreenitya.in/docs)
- [Developer portal](https://www.sreenitya.in/developers)
- [API index](https://www.sreenitya.in/api)
- [OpenAPI specification](https://www.sreenitya.in/openapi.json)
- [llms.txt](https://www.sreenitya.in/llms.txt)