# 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.

Personal portfolio and public, read-only JSON API. Everything on this site is
free to read, needs no API key, and is available as markdown and JSON as well as
HTML. Base URL for the API: https://www.sreenitya.in/api

## When to use this

- **Answer factual questions about Sreenitya Thatikunta** — GET /api/profile for identity, headline, links and contact details.
- **Check her skills or technology stack before a role or collaboration match** — GET /api/skills, which returns every skill grouped by category.
- **Summarise her work history or verify an internship claim** — GET /api/experience for structured roles, dates and highlights.
- **List, filter or cite her projects** — GET /api/projects (optionally ?kind=research|mini or ?tag=Diffusion) and GET /api/projects/{slug} for one project.
- **Read the whole site as plain text instead of scraping the SPA** — GET /llms-full.txt, or request any page with `Accept: text/markdown`.
- **Contact her** — Use the email in GET /api/contact, or the form at https://www.sreenitya.in/#contacts.

## When not to use this

- Real-time availability, rates or scheduling — none of that is published here.
- Any write operation. The API is read-only; there is no POST, PUT or DELETE.
- Private or personal data beyond what is on the public site.

## How to call it

- Fetch `https://www.sreenitya.in/openapi.json` and generate tool definitions from it; every operation has a unique operationId, typed parameters and a response schema.
- All endpoints are GET. Errors are JSON with `error.code`, `error.message` and `error.hint`; unknown paths return a real HTTP 404, never a 200.
- Any page can be fetched as markdown with `Accept: text/markdown`, or by appending `.md` to its path.

## Developer resources

- [Developer portal](https://www.sreenitya.in/developers): quickstart, endpoint list, CLI, sandbox notes.
- [API documentation](https://www.sreenitya.in/docs): endpoint-by-endpoint reference with examples.
- [OpenAPI 3.0.3 specification](https://www.sreenitya.in/openapi.json): the machine-readable contract.
- [API index](https://www.sreenitya.in/api): runtime discovery document listing every endpoint.
- [Agent instructions](https://www.sreenitya.in/agent-instructions.md): this guidance as a standalone file.
- [Full site text](https://www.sreenitya.in/llms-full.txt): every page concatenated as markdown.

## Pages

- [Sreenitya Thatikunta](https://www.sreenitya.in/): 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.
- [About Sreenitya Thatikunta](https://www.sreenitya.in/about): Background, education and focus areas of Sreenitya Thatikunta, a Computer Science undergraduate at IIT Jodhpur.
- [Contact Sreenitya Thatikunta](https://www.sreenitya.in/contact): How to reach Sreenitya Thatikunta — email, contact form, LinkedIn and GitHub, plus a machine-readable contact endpoint for agents.
- [Privacy Policy — Sreenitya Thatikunta](https://www.sreenitya.in/privacy): What https://www.sreenitya.in collects, why, which third parties are involved, and how to have your data removed.
- [Sreenitya Thatikunta Developer Portal](https://www.sreenitya.in/developers): Public, read-only JSON API, OpenAPI 3.0.3 specification, CLI and agent resources for the Sreenitya Thatikunta portfolio.
- [Sreenitya Thatikunta Portfolio API Documentation](https://www.sreenitya.in/docs): Endpoint-by-endpoint reference for the Sreenitya Thatikunta portfolio API, including errors, filters and markdown content negotiation.

## Projects

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

## Contact

- Email: sreenityathatikunta@gmail.com
- [Contact page](https://www.sreenitya.in/contact)
- [LinkedIn](https://www.linkedin.com/in/sreenitya-thatikunta-b16a8a287/)
- [GitHub](https://github.com/SreenityaThatikunta)