Skip to content
View mirfan899's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report mirfan899

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mirfan899/README.md

👋 Hi, I'm Muhammad Irfan

AI Engineer | Computer Vision | LLMs | Full‑Stack Product Builder

I build AI-powered products end‑to‑end — from data pipelines and machine learning models to full-stack deployment, APIs, cloud infrastructure, and mobile/computer vision applications.

My work spans:

  • 🎙️ Voicebots & Speech AI
  • 🤖 LLM-based workflow automation
  • 🧠 RAG systems & embeddings
  • 🛰️ Geospatial analysis (GEE, QGIS)
  • 📱 Mobile AI (Android, React Native)
  • 🎥 AI video processing, TTS, and media intelligence
  • 🖼️ Image matching, feature extraction, and AR
  • 🛠️ Full-stack development (Next.js, Prisma, MySQL, AngularJS)

🚀 What I’m Building / Recent Work

1. AI Voicebot SaaS

  • Custom voicebots for businesses
  • Real‑time conversation, intent detection, contextual memory
  • API integrations for CRM, scheduling, invoicing

2. Video → Shorts AI Tool (MVP)

  • Auto‑detection of highlight moments
  • Intelligent cut detection
  • Auto‑captions, transitions, template‑based layout
  • Built pipeline for speech‑to‑text + LLM chunking + editing

3. Media Monitoring Platform

  • Speech-to-text + OCR for news tickers
  • Topic classification using LLMs
  • Sentiment & headline analysis
  • Dashboard and alert system

4. Mobile AR + Vector Search (Android)

  • Kotlin + ObjectBox vector DB
  • Real‑time feature extraction & matching
  • Video frame–based querying and overlay

5. PDF → Audiobook Agent

  • Chapter-wise extraction
  • Speech synthesis using Orpheus‑TTS
  • Summaries, highlights, structured content output

🚀 Core Skills

Skill Level
AI / ML AI/ML
LLMs / RAG LLMs/RAG
Computer Vision Computer Vision
Full-Stack Full-Stack
Mobile / Android Mobile
Speech / TTS Speech
Video Processing Video

Languages & Tools

AI / ML
PyTorch TensorFlow Lite scikit-learn XGBoost Milvus FAISS ObjectBox

LLMs
OpenAI Ollama Transformers RAG Embeddings

Speech
Orpheus-TTS Whisper VAD Diarization

Computer Vision
OpenCV LoFTR LightGlue Kornia Image Matching

Mobile
Android React Native

Full-Stack
Next.js AngularJS Prisma MySQL Tailwind JWT

Cloud / DevOps
Azure Docker FastAPI REST API

GIS
GEE QGIS Raster/Vector Analysis


📈 Experience Snapshot

pie title Skills Distribution
  "AI/ML" : 30
  "LLMs/RAG" : 20
  "Computer Vision" : 20
  "Full‑Stack" : 15
  "Mobile/Android" : 10
  "GIS" : 5
Loading

📊 GitHub Stats

Irfan's GitHub stats

Top Languages


🏆 GitHub Trophies

Trophies

🌐 Social Links


📬 Let's Work Together

If you're building something with:

  • AI automation
  • RAG + LLMs
  • Voice or video AI
  • Android vision apps
  • Geospatial analysis

I’d love to collaborate.

Reach out anytime! 🚀

Pinned Loading

  1. Urdu Urdu Public

    Collection of Urdu datasets for POS, NER, Sentiment, Summarization and NLP tasks.

    72 19

  2. RasaHQ/rasa RasaHQ/rasa Public

    💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

    Python 20.9k 4.9k

  3. ubot ubot Public

    Code of tutorial https://www.urdunlp.com/2020/04/building-conversational-chat-bot-for.html

    Python 4 3

  4. rasa-qa-bot rasa-qa-bot Public

    question answer bot

    Python 5