02 — Work
Featured Projects
Full-Stack SaaS · AI Assistant · Real-time Collaboration
NexTask — AI-Powered Project & Task Management SaaS
NEXTASK — FLOW
Built solo from zero to production in 5 months. NexTask replaces the gap between Linear (too rigid) and Notion (too unstructured) for small technical teams — real-time collaborative Kanban, Flow (the git-style visual project map shown above), and Nex, an AI assistant that creates and summarizes tasks via the Anthropic API. Multi-tenant data isolation enforced at the database layer with PostgreSQL Row Level Security.
React 18
TypeScript
Tailwind CSS
Supabase
Anthropic API
Three.js
Framer Motion
Vercel
PROJECT_02
Quantum SVM — Network Intrusion Detection
Quantum vs Classical · KDD Cup 99 · Streamlit + React
Implemented a Quantum SVM using Qiskit's ZZFeatureMap and FidelityQuantumKernel to classify network intrusions on the KDD Cup 99 dataset. Benchmarked quantum kernel performance head-to-head against a classical RBF-SVM across accuracy, F1, and ROC-AUC. Built a React 18 + Three.js landing page and a Streamlit dashboard with precomputed cached results.
Python
Qiskit
Scikit-learn
Streamlit
React 18
TypeScript
Three.js
Vercel
PROJECT_03
Pulsar Star Detection as a Service
99% Accuracy · ROC-AUC 0.973
Cloud-deployed ML microservice using FastAPI + LightGBM to classify pulsar candidates from telescope features. Independent microservices for ingestion, preprocessing, inference, and storage. Streamlit dashboard with batch predictions, SHAP interpretability, and EDA visualizations deployed on AWS EC2.
FastAPI
LightGBM
Streamlit
Docker
AWS EC2
PostgreSQL
Redis
Optuna
More Projects (academic / coursework)
PROJECT_04
Cross-lingual Sentiment Analysis
Zero-shot & Fine-tuned · 3 Transformer Models
Multilingual emotion-classification workflows using mBERT, XLM-R, and XLNet. Evaluated across multi-domain datasets with reproducible benchmarking pipelines and optimized tokenization strategies.
PyTorch
HuggingFace
mBERT
XLM-R
XLNet
Scikit-learn
PROJECT_05
Chest X-Ray Classification CNN
AUC 0.99 COVID · 0.98 Pneumonia · 0.97 Normal
CNN models to classify chest X-rays into COVID-19, Pneumonia, and Normal categories. Applied data augmentation, EDA, and GPU-accelerated training to reduce overfitting on imbalanced medical imaging datasets.
TensorFlow
Keras
OpenCV
CNN