Software Engineer building backend systems, AI applications, and real-time software.

github

Mohamad shafeez  • Peerlist

Built a real-time auction platform with Admin, Seller, and User roles. Implemented live bidding using Socket.io where updates reflect instantly for all users. Built role-based chat system and secured backend APIs using JWT authentication and RBAC. Used Cloudinary for image uploads and MongoDB for storing auction, bids, and chat data.

🏠Auction House | Real-Time Property Bidding 

A fully offline AI system built to run voice commands, AI tasks, and system automation directly on the local machine without cloud dependency. Built a real-time voice system using Faster-Whisper for speech-to-text and Ollama local models for reasoning. Supports voice commands, automation workflows, debugging tasks, and local AI execution. with low latency and maintains conversation context. Designed a modular architecture where each feature is a separate Python skill module. New features can be added by dropping a file into the system without touching core code. Built system automation using ADB, allowing voice control of Android devices — opening apps, sending messages, navigation, and checking device status. Implemented a dual-mode system: Fast mode for instant voice responses Heavy mode for complex AI tasks like debugging and automation Added worker isolation using multiprocessing so heavy AI tasks never block voice input. Built a live monitoring dashboard showing system status, active tasks, CPU/RAM usage, and execution logs in real time. Includes automatic recovery system that restarts failed or frozen AI workers without stopping the main system. Added process monitoring and watchdog recovery that automatically detects frozen workers and safely restarts them without affecting the main voice system. Implemented separate fast-response and heavy-workflow execution paths to keep voice interaction responsive during long AI tasks. 🔗 Demo Video: https://drive.google.com/file/d/15aT0SbL-bgEsEy-pLC1-Gyj09cFdAkgW/view?usp=sharing

🤖 Cipher — AI Voice Assistant / Local AI Run

Built a full-stack travel safety platform that analyzes live weather, AQI, traffic, and user health conditions to generate safe travel recommendations. Developed a route safety engine that compares fastest vs safest paths using TomTom API and environmental data. Integrated Gemini AI to generate simple safety advice and travel suggestions based on live conditions. Added features like OCR text extraction, voice alerts, AI chat assistant, offline support using Service Workers, and Firebase authentication. Handled production issues like CSP restrictions, API routing, and deployment across Vercel, Render, and Firebase. Built interactive map-based safety analysis with live alerts, route comparison, and AI-assisted travel planning. 🔗 Demo Video:  https://drive.google.com/file/d/1Bc9oYDfGGSERi5KU-XpOtrF12JbCOkti/view?usp=drive_link

🗺️SafeNav — AI-Powered Travel Safety PWA

Built a secure voting system using MERN stack with role-based access control. Ensured vote integrity using unique constraints (userId + pollId) to prevent duplicate voting. Designed REST APIs with proper validation, authentication, and admin monitoring dashboard.