Featured Work
All Projects
Full-stack applications, ML systems, and cloud architectures built with production-grade patterns.
Showing 8 of 8 projects
ProfiLens
Full-Stack Career Development Platform with gamified learning, MCQ + coding exams, AI-powered resume generation, and a coin-based reward store. Built with Django, DRF, PostgreSQL, and WeasyPrint for PDF generation.
Built async resume/PDF generation with RBAC-backed learning workflows.
Key Engineering Challenges
- RBAC authorization system
- Async PDF generation pipeline
- PostgreSQL schema design & indexing
- Service-oriented architecture
Personal Cloud Assistant
Fully serverless AWS application for secure note and file management. Uses Lambda + API Gateway for REST APIs, S3 pre-signed URLs for file I/O, DynamoDB for storage, Cognito for auth, and CloudWatch for monitoring.
Shipped secure serverless notes and file storage with Cognito and S3 pre-signed URLs.
Key Engineering Challenges
- Serverless architecture design
- S3 pre-signed URL security
- DynamoDB data modeling
- Cognito authentication flows
TeamSense
AI-Powered HR Intelligence Platform built for a hackathon. Features DRF APIs, async ingestion pipelines via Celery + Redis, PostgreSQL models, React dashboard, and Dockerized deployment.
Designed async HR intelligence pipelines with Celery, Redis, and Dockerized services.
Key Engineering Challenges
- Async task queues with Celery
- Redis caching strategies
- PostgreSQL relationship modeling
- Docker containerization
Animal Classification
Deep learning project classifying images into 15 animal categories using MobileNetV2 transfer learning. Features data augmentation, early stopping, and a Streamlit web app for predictions.
Trained and deployed transfer-learning inference for 15-class image classification.
Key Engineering Challenges
- Transfer learning with MobileNetV2
- Data augmentation strategies
- Early stopping implementation
- Model deployment pipeline
Color Classifier
ML web app that analyzes and visualizes dominant color distribution in images. Uses Random Forest classifier on custom-labeled color dataset with OpenCV for feature extraction and Streamlit for the UI.
Delivered real-time dominant-color prediction with OpenCV feature extraction.
Key Engineering Challenges
- Custom dataset labeling
- Feature extraction with OpenCV
- Random Forest model training
- Streamlit real-time inference
GestureMediaPlayer
Computer vision application that controls media playback using hand gestures. Uses MediaPipe for real-time hand tracking and gesture recognition with OpenCV for video processing.
Implemented low-latency hand-gesture controls for desktop media playback.
Key Engineering Challenges
- Real-time hand tracking
- Gesture recognition accuracy
- Low-latency video processing
- Cross-platform compatibility
n8n Workflow
Custom n8n workflow automation for data processing and integration. Features automated triggers, API integrations, and conditional logic for complex business processes.
Automated API-triggered workflows with conditional routing and retry-aware handling.
Key Engineering Challenges
- Workflow orchestration
- API integration patterns
- Error handling and retry logic
- Data transformation pipelines
Automated Book Workflow
End-to-end automation system for book processing and management. Integrates multiple APIs for metadata extraction, content processing, and automated publishing workflows.
Orchestrated multi-service book processing with resilient workflow state management.
Key Engineering Challenges
- Multi-service integration
- Workflow state management
- Error recovery mechanisms
- Scalable architecture design