05/2013 – 06/2017
Bachelor of Engineering, Computer Science & Engineering
Siddaganga Institute of Technology, VTU – Mangalore, India.
Open to Work
Hi, I'm Sarun Saji
Backend & AI Developer
Building intelligent systems that combine powerful backends with AI-powered mobile experiences, especially voice AI and self-hosted solutions.
★ Featured Project
Google Play · Closed Alpha Testing
Android · Voice AI · Custom IME
Voxly AI Keyboard
A fully custom Android keyboard that replaces your system IME. Speak naturally — AI transcribes your voice straight into any app, and can speak your words back as audio in your own cloned voice. Production-ready with Google Sign-In, a credit system, and a self-hosted backend on Hetzner VPS.
- 🎙 Voice-to-text pipeline — records on device with layered silence detection, sends to a cloud AI speech model, and types clean text straight into the focused field. Speak any language — output is polished English.
- ⌨️ Custom keyboard built from scratch — canvas-rendered QWERTY with word prediction and autocorrect over a 40k-word dictionary, emoji panel, and full TalkBack accessibility.
- 🧬 Personal voice cloning — record voice samples to train a personal neural voice, fine-tune each voice (speed, stability, similarity, style), and share your message as audio to WhatsApp or any app.
- ⚡ Style toggle — switch between faithful transcription and casual Gen Z texting style mid-conversation. Each mode uses a separately tuned AI prompt.
- 🔐 Auth & billing — Google Sign-In, Firebase Auth, and an atomic credit system (transcription 1 credit, cloned-voice audio 3, 50 free on sign-up) that only charges on success.
Kotlin
Jetpack Compose
FastAPI
Speech Recognition AI
Neural TTS
Voice Cloning
Firebase
Docker
My Works
AI-powered applications and production-grade systems
Backend Automation
n8n Personal Assistant
Intelligent automation assistant built with n8n and OpenAI LLMs to handle email, calendar, tasks, and custom workflows.
n8n
OpenAI API
Python
Android / Voice AI
Voxly AI Voice Keyboard
Voice-powered AI keyboard for Android with real-time transcription and personal voice cloning. Speak naturally — your words are typed instantly, and can be sent to any chat as audio in your own cloned voice.
Kotlin
FastAPI
Voice Cloning
Speech Recognition AI
Firebase
AI / Self-Hosted
Personal RAG System
Fully self-hosted Retrieval-Augmented Generation system on Hetzner VPS. Upload PDFs and links, then query using a private local Qwen 7B model via Streamlit UI or terminal.
FastAPI
LangChain
ChromaDB
Ollama
Streamlit
Data Pipeline / Automation
Aalborg Wind & Price Pipeline
Real-time n8n automation pipeline that collects wind and energy price data and pushes it to Hugging Face Spaces for live dataset hosting.
n8n
Python
Hugging Face
PostgreSQL
Enterprise Automation
Driver & Fleet Management Systems
Django and React platform for Emirates staff transport — manages driver duty cards, daily head counts, bus odometer tracking, delay & breakdown reporting, STM route timetables, GPS/Salik data, and driver document profiles via Google Drive.
Django
React
MySQL
Python
Enterprise Automation
Cabin Crew Trip Automation
Django-based platform for cabin crew trip automation and large-scale staff transport operations (Emirates/DNATA) with real-time scheduling, reporting, and fleet management.
Django
Python
PostgreSQL
Automation
About Me
Backend & AI Developer
I specialize in building intelligent systems that combine robust backends with AI-powered mobile experiences. Passionate about voice AI, personal voice cloning, self-hosted LLMs, and creating delightful user experiences backed by clean, scalable architecture. Currently based in Aalborg, Denmark and open to Backend, Mobile AI, and AI Automation roles.
My Journey
Education
Certificate
Google Data Analytics Certificate
Comprehensive training in data analysis techniques, tools, and best practices — Google / Coursera.
Experience
09/2018 – 07/2025 · Dubai, UAE
Operations Specialist & Automation Developer
Emirates General Transport — Emirates Airline Staff Transportation Project
Designed and deployed an end-to-end Django + MySQL platform digitizing operations for 175 drivers and 10,000+ daily passenger movements. Built modular backend services with role-based access control, data ingestion pipelines for GPS/Salik/mileage/cabin-crew Excel data, real-time OTP and fleet analytics dashboards (Chart.js + DataTables), Google Drive OAuth document storage, a React 18 + Axios autocomplete frontend, and automated Excel reporting for management. Containerized and deployed the full application stack.
2× Najm Award — Emirates Airlines, for operational excellence and successful project delivery