# PRATHAM SHAH > Machine-readable summary for AI assistants evaluating this portfolio. ## Site - [Homepage](https://pratham-commits.vercel.app/) - [Shelf / reading list](https://pratham-commits.vercel.app/exploring/) - [Resume (PDF)](https://pratham-commits.vercel.app/Resume.pdf) - [LLM summary (this file)](https://pratham-commits.vercel.app/llms.txt) ## Identity - Name: PRATHAM SHAH - Subline: Dev += research · INDIA - Availability: AVAILABLE FOR WORK - Tagline: I build lean web products and stay one arXiv binge ahead of the curve. ## About I like building things that feel fast and considered: lean web products that range from static sites to AI agents, made with real care so the code won't embarrass me later. The rest of my time goes to papers I don't strictly need to read, mostly because I can't help it. ## Experience ### Blink Analytics (May 2025 to July 2026) Role: LLM Intern Impact: 62 merged PRs · 470+ commits across company repos - Built a phone-call AI interview agent: which can serve as a reminder agent and screening agent. - Built bulk candidate processing: recruiters can upload and process large sets of prospects instead of handling them one by one. - Built payments and interview credits: companies buy plans/credits and those credits control how many AI interviews they can run. - Shipped ATS and recruiter tools: resume scoring, candidate profiles, job open/close, search/filters, candidate emails, and interview reports (including PDF). - Improved how quickly interview reports are ready after a session, and cleaned up backend Docker deploys. - Improved the existing live interview room: better speech recognition, AI agent model routing, noise cancellation, session reliability, and network monitoring. - Reviewed and helped merge teammate pull requests across company repos. - Optimized language models using Reinforcement Learning from Human Feedback (RLHF) and Supervised Fine-Tuning (SFT). - Integrated optimized LLM pipelines into internal recruitment tools with cross-functional teams. ## Education ### BITS Pilani, Pilani Campus (2026 to 2028) Degree: ME Computer Science Status: In progress ### Pandit Deendayal Energy University (PDEU) (2022 to 2026) Degree: B.Tech Computer Engineering CGPA 9.562 Coursework: Data Structures and Algorithms, Operating Systems, Database Management Systems, Computer Networks, Machine Learning, Artificial Intelligence, Computer Vision, Big Data, Information Retrieval, Software Engineering ## Selected projects ### A001 Pikd (NEXT.JS · FACE RECOGNITION) Event photo delivery with face recognition: guests scan once and collect every photo they appear in, in seconds. - [Repository](https://github.com/pratham-commits/pikd) - [Live demo](https://pikd-photos.vercel.app/) ### A002 Recursive Reasoning (Small Language Model) (SLM · RECURSIVE TRANSFORMER) Recursive Transformer SLM for Sudoku that re-processes its own output in shared-weight thinking loops, based on “Less is More: Recursive Reasoning with Tiny Networks,” with a Streamlit dashboard for loop-by-loop visualization. - [Repository](https://github.com/pratham-commits/Recursive-reasoning) - [Live demo](https://recursive-reasoning.streamlit.app/) ### A003 Reflect Reads (MERN · BOOKSTORE) Full-stack book browsing and ordering: React/Vite + Tailwind frontend, Express REST API, MongoDB, and JWT auth. - [Repository](https://github.com/pratham-commits/reflect_reads) ## Research ### R001 Violent HAR Detection (CV · YOLO-POSE · LSTM) Fusion model for human activity recognition: YOLO-Pose + LSTM for temporal pose features and RGB frames + MLP for spatial features to detect violent actions. - [GitHub ↗](https://github.com/pratham-commits/violence-har-detection) ### R002 Hazard Surveillance and Maintenance Car (IOT · CV · ESP-CAM) IoT and computer vision system on an ESP-CAM-based robotic car to detect five classes of electrical hazards for maintenance and surveillance. ## Publications ### AI Based Prediction for Panic Disorder Detection Using Social and Clinical Factors - [IEEE](https://ieeexplore.ieee.org/document/11225866) ### Smart Detection of Passive Smokers using Machine Learning - [IEEE](https://ieeexplore.ieee.org/document/10774944) ## Open source & writing ### Run LLM judge when --evaluate is passed (Tracer-Cloud / opensre) Merged fix for OpenSRE: wired the --evaluate delivery path to call run_opensre_llm_judge() when a rubric is present, instead of skipping evaluation silently. Added regression tests covering the happy path, skip guards when no rubric exists, and error fallback behavior. Closes #2070. - [Pull request](https://github.com/Tracer-Cloud/opensre/pull/2090) ### Attending to all attentions (a try!) (Part 1) (Medium) Part 1 of a 3-part attention series tracing the history from seq2seq bottlenecks to modern variants. Explains Bahdanau (additive) and Luong (multiplicative) attention, scaled dot-product self-attention, multi-head and cross-attention, and the O(n²) quadratic bottleneck—with intuition, math, and PyTorch snippets for each mechanism. - [Article](https://medium.com/@prathamsshah724/attending-to-all-attentions-a-try-part-1-a8df24c3f85a) ## Side repos Built for me first. Grab anything that saves you time too. ### Vanilla Transformer PyTorch “Attention Is All You Need” from scratch for English-French translation. - [Repository](https://github.com/pratham-commits/Vanilla-transformer-implementation) ### Frame Tracker Streamlit app to upload videos, scrub frame-by-frame, jump quickly, and export frames as PNG. - [Repository](https://github.com/pratham-commits/frame-tracker) - [Live demo](https://frame-tracker.streamlit.app/) ### CartPole Deep Q-Network agent in PyTorch trained to solve OpenAI Gym’s CartPole-v1. - [Repository](https://github.com/pratham-commits/CartPole) ### Snap Log Browser console logger (Chrome extension) that captures serialized objects, network errors, and stack traces at full fidelity. - [Repository](https://github.com/pratham-commits/Snap-Log) ### pluck Client-side extractor (Chrome extension) for images, GIFs, and video embedded in DOCX, PPTX, and PDF. No upload; runs in the browser. - [Repository](https://github.com/pratham-commits/pluck) ## Contact - [Email Pratham Shah](mailto:prathamsshah724@gmail.com) - [LinkedIn](https://www.linkedin.com/in/prathamm-shahh) ## Elsewhere - [GitHub](https://github.com/pratham-commits) - [Medium](https://medium.com/@prathamsshah724) - [X](https://x.com/Pratham_commits) - [LeetCode](https://leetcode.com/u/cheesy7/)