About Me
I build AI systems that make real-world services accessible to everyone.
I'm Praneeth, an AI & Data Science student at Karunya Institute of Technology and Science, driven by one goal: building systems that work in the real world. My work spans computer vision, NLP, and end-to-end ML pipelines - from raw data to deployed product.
I've shipped a tutoring platform to a paying client, built a gesture-controlled presentation system using OpenCV and MediaPipe, and developed an AI coding assistant using RAG and LangChain. I also built a fisherman border-detection system as a proof of how AI can protect lives.
Status
B.TECH 2nd year at Karunya Institute of Technology and Sciences
Core Stack
Python, SQL, Machine Learning , MERN
Focus
Deployed AI systems
Technical Proficiency
AI & Machine Learning
Frameworks & Libraries
Languages
Web & APIs
Domains & Concepts
Data & Backend
MLOps & System Design
Featured Projects
VOX — AI-Powered Exam Scribe Platform
A fully voice-navigated examination platform that replaces human scribes for students with accessibility needs. Designed for zero dependency on external humans during exams.
- Docker + Nginx + MongoDB · PWA with offline support · 13+ voice commands
- LLaMA 3 via Ollama for MCQ answer formatting · Web Speech API for STT/TTS
Multirole EdTech Delivery Platform
Full-stack tutoring platform with distinct student, tutor, and admin roles — shipped to a paying client.
- Role-based access · separate dashboards
- Live in production · delivered to a real client
Automated Commerce Pipeline
An end to end order management system over Whatsapp SMBs - zero app install required for the end customer.
- Webhook-driven order ingestion via mete WA cloud API - n8n workflow orchestration
- Razor Pay REST API for payment initiation - Google sheets as persistent datastore
Real-Time Hand Landmark Slide Controller
Controls slides hands-free using real-time hand gesture detection at 30+ FPS.
- 30+ FPS · works with any software
- Configurable swipe threshold in config.py
StayLive - Uptime Monitoring Service
Automated uptime monitoring that keeps free-tier backends alive by executing periodic HTP health -check polling against registered endpoints.
- Cron-scheduling polling , mitigates provider-side cold start hibernation
- Serverless deployment on vercel - lightweight zero config setup
Linguistic Pattern Based Fake News Detector
NLP pipeline that classifies misinformation in news articles with multi-model benchmarking.
- Multi-model benchmarking + evaluation metrics
- Raw text → features → classifier → prediction
Get In Touch
Send a Message
Fill out the form and I'll get back to you
Connect With Me
Find me on social platforms