SWASTIDIP MAJI
AI/ML Engineer & Deep Learning Specialist | Full-Stack Developer | Data Science Undergraduate
Proactive and results-driven Computer Science & Engineering student specializing in Data Science with a strong focus on AI/ML, Deep Learning, and Computer Vision. Adept at building scalable full-stack applications and deploying robust machine learning pipelines. National Finalist in ISRO BAH 2025. Eager to leverage strong technical skills and innovative problem-solving to contribute to cutting-edge projects.
Tech Stack
Tools and technologies I use to bring ideas to life
Languages
Machine Learning & AI
Deep Learning & Computer Vision
NLP & LLMs
Web & API Frameworks
Data Science
DevOps & Tools
Featured Projects
A selection of my recent work and open-source contributions
MedXpress – Healthcare SaaS Platform
Developed end-to-end healthcare SaaS with appointment booking, medication ordering, and AI-powered health insights. Architected REST API handling 40+ endpoints for appointments, medications, lab reports, and AI health recommendations. Implemented advanced medication catalog search with fuzzy matching, synonym expansion, and caching for < 100ms response.
Legal-Eagle-Ultimate – Multi-Agent AI Legal Assistant
Engineered multi-agent orchestration coordinating 5 specialized Gemini-2 agents for risk assessment and compliance checks. Implemented InLegalBERT fine-tuned NER pipeline for Indian statute recognition with section/act retrieval across 1872+ provisions. Architected document processing combining pdfplumber, Google Document AI OCR, and RAG vector embeddings for advice generation.
ISRO BAH 2025 – Tropical Cloud Cluster Detection
Built CNN-based Tropical Cloud Cluster detection system processing 500MB+ HDF5 satellite imagery with 99%+ accuracy. Architected automated pipeline processing half-hourly INSAT files with real-time monitoring and CSV/JSON exports. Deployed Next.js dashboard on Vercel with side-by-side visualization, geospatial mapping, and temporal filtering UI.
More Projects
Roadguard-MVP – Computer Vision Road Safety System
Trained YOLOv11n on 6,439 images achieving 50.3% mAP@0.5; deployed with 45ms inference and 22 FPS video processing. Built GDPR-compliant privacy pipeline with OpenCV face/plate anonymization, batch processing 100+ images with verification. Implemented DBSCAN clustering (10m radius) with SQLite for hazard deduplication, reducing false alarms by 90% via Folium maps.
Market-Shield – Multi-Channel Fraud Detection
Built multi-channel fraud detection ingesting URLs, PDFs, images, and videos; implemented EasyOCR + Tesseract with OpenCV verification. Developed RAG architecture using FAISS vector search with Gemini embeddings for real-time SEBI policy retrieval. Deployed risk scoring engine detecting pump-and-dump, guarantee claims; integrated caching, rate limiting, and audit trails.
Work Experience
My professional journey and key contributions
National Finalist
- ▹Selected among top 50 teams from 8000+ nationwide entries for ML-powered satellite data processing innovation
- ▹Pitched AI-driven geospatial analytics platform to ISRO scientists and space technology industry leaders
- ▹Collaborated with cross-functional team using Agile sprints and Git workflows for rapid ML model deployment
Merit Scholarship Recipient
- ▹Awarded competitive merit-based West Bengal Government scholarship (Top 10%) for 3 consecutive years, recognizing sustained academic excellence and performance
Open Source Contributor & Technical Lead
- ▹Built 5 open-source AI/ML applications with CNN-based cloud detection (ISRO-BAH-2025), YOLOv11n object detection (RoadGuard), FAISS semantic search (MarketShield), and RAG systems (Legal-Eagle), all deployed with live demos and comprehensive documentation
- ▹Architected production ML pipelines using TensorFlow, OpenCV, FAISS, and Gemini API integrations, with Next.js/Streamlit frontends and automated processing workflows across Python/TypeScript codebases
Get in Touch
Have a project in mind or want to collaborate? I'd love to hear from you!
SWASTIDIP MAJI
Open to opportunities
Prefer email directly? swastidip2004@gmail.com