Things I've built.

VoxRAG is a voice- and text-enabled Retrieval-Augmented Generation system built on MSMARCO-XI. Speak or type in English, हिन्दी, मराठी, বাংলা, മലയാളം, ગુજરાતી, অসমীয়া — the pipeline transcribes, retrieves grounded passages from ~3.2M (32 lakh) embedded records, and streams a cited answer back, targeting <200 ms retrieval / time-to-first-token.

• Python
• Streamlit
• SarvamAI
• Groq

Won the AAIPL Hackathon (1st place out of 120 teams) by building a dual-agent LLM system using Qwen2.5-14B-Instruct. Developed end-to-end fine-tuning pipelines with LoRA and 4-bit quantization to train a Question Agent for generating MCQs and an Answer Agent for solving them with structured reasoning. Implemented robust data cleaning, custom dataset formatting, and efficient training workflows for high performance under constrained compute.

• Python
• Jupyter Notebook
• UnSloth
• LoRa

The Diary is a minimal, distraction-free social platform built for busy professionals to stay connected with family and close friends through daily journal entries and quick personal notes—without the clutter of traditional social media.

• Nextjs
• Postgresql
• Tailwind CSS
• Prisma ORM

AI-enabled detection of exoplanets from noisy TESS light curves, using a Box-Least-Squares transit search feeding a calibrated XGBoost + Random-Forest ensemble, plus an LLM (via Groq) that explains and discusses each result with you.

• Python
• Jupyter Notebook
• XGBoost
• Groq

A reproducible machine learning pipeline for cattle breed classification from SNP genotype data, featuring CNN and Transformer baselines. Includes data validation, preprocessing, training, and benchmarking workflows to compare local vs long-range genomic pattern modeling.

• Python
• Jupyter Notebook
• PLINK
• NumPy

Labeled custom conveyor belt data and trained a YOLOv8 model from scratch. Increased detection accuracy from 72% to 80% with model tuning and augmentation.

• Python
• OpenCV
• Roboflow
• YOLOv8 (Ultralytics)

RubricAI is a powerful Next.js application designed for educators and students to evaluate assignments against custom rubrics using Genkit AI. It features batch processing, Cloudinary file storage, and academic integrity monitoring.

• Nextjs
• TypeScript
• GenKit
• Postgresql

A Python-based attendance system that utilizes facial recognition to accurately identify students and mark their attendance on specific dates.

• Python
• OpenCV
• Face Recognition
• Pandas