https://github.com/rayyan9477/rayyan9477

My professional introduction
https://github.com/rayyan9477/rayyan9477

cronjob github github-actions readme readme-profile

Last synced: 2 months ago
JSON representation

My professional introduction

Host: GitHub
URL: https://github.com/rayyan9477/rayyan9477
Owner: Rayyan9477
Created: 2025-08-01T11:35:15.000Z (11 months ago)
Default Branch: main
Last Pushed: 2025-10-02T08:15:41.000Z (9 months ago)
Last Synced: 2025-10-02T10:14:29.819Z (9 months ago)
Topics: cronjob, github, github-actions, readme, readme-profile
Language: Python
Homepage:
Size: 11.8 MB
Stars: 2
Watchers: 0
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

### 📊 **Live Stats Dashboard**

1,895

_{👁️ Profile Views}

71

_{🤝 Followers}

146

_{⭐ Total Stars}

256

_{🔥 Day Streak}

---

## 🚀 About Me

AI Development

### 🎯 **Current Mission**
Building production AI systems at **Nobility RCM** — architecting agentic workflows, medical compliance automation, and LLM integrations that replace hours of manual work with a single pipeline.

### 💼 **Experience**

**AI Engineer** | **Nobility RCM** | Islamabad, Pakistan | March 2025 – Present

- Developed a medical compliance agent that reads clinical notes and auto-extracts ICD-10/CPT/HCPCS billing codes using a fine-tuned Phi-3 model with a 4-agent LangGraph architecture and 3-layer anti-hallucination validation — replacing hours of manual medical coding with a single pipeline.
- Built LLM-powered browser automation agents (Playwright + Browser Use) that navigate billing portals, extract claim data, and auto-fill forms — turning repetitive manual workflows into agentic AI processes, cutting processing time by 15% and boosting accuracy by 10%.
- Designed RAG pipelines with hybrid retrieval (FAISS vectors + BM25 keyword matching) and MCP server integrations to connect LLMs with internal billing systems, enabling natural-language querying across claim databases and accelerating decision-making by 10%.

### 🌟 **Philosophy & Vision**
```python
class AIEngineer:
def __init__(self):
self.mission = "Democratizing AI accessibility"
self.passion = "Building intelligent systems that augment human potential"
self.mantra = "The best way to predict the future is to invent it!"

def current_focus(self):
return [
"Advanced Transformer Architectures",
"Multimodal AI Systems",
"Production MLOps",
"Open Source Contributions"
]
```

## 🏆 Featured Projects

### 🌟 **Premium Project Showcase**

### 🔮 **Solace AI - Advanced Mental Health Assistant**
*Revolutionary AI-Powered Mental Wellness Platform*

Solace AI Demo

🌟 **Enterprise-Grade Mental Health AI** with cutting-edge therapeutic conversation capabilities
🧠 **Advanced NLP Models** for empathetic response generation and emotional intelligence
🔒 **HIPAA-Compliant Architecture** ensuring maximum privacy and data security
📊 **Real-time Analytics Dashboard** for mental health professionals and researchers
🚀 **Scalable Microservices** deployed on AWS with auto-scaling capabilities

**Premium Tech Stack:** `Advanced Transformers` `Therapeutic NLP` `AWS Cloud` `Redis` `PostgreSQL` `Docker` `Kubernetes`

[![View Premium Project](https://img.shields.io/badge/🔮%20View%20Solace%20AI-6C5CE7?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Rayyan9477/Solace-AI)
[![Documentation](https://img.shields.io/badge/📚%20Docs-A29BFE?style=for-the-badge&logo=gitbook&logoColor=white)](#)

### 💎 **Other Notable Projects**

#### � **LinkedIn MCP Server**
LinkedIn's API is locked down and most job tools are half-baked wrappers. I built a full MCP (Model Context Protocol) server that gives any LLM-based assistant a structured tool interface to LinkedIn — search jobs, generate tailored resumes and cover letters, and manage applications programmatically. Plugs directly into Claude Desktop, Cursor, or any MCP-compatible client. No scraping, no hacks — clean protocol-level access.

**Stack:** `Python` `MCP` `LinkedIn API` `LLM` `FastAPI`

[![View Project](https://img.shields.io/badge/View_Project-FF6B6B?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Rayyan9477/linkedin_mcp)

#### 📄 **Agentic Document Extraction**
Most OCR tools choke on messy scans — broken tables, mixed layouts, multiple records per page. Built an enterprise extraction system that auto-detects document type, generates adaptive schemas on the fly (zero-shot), and extracts multiple records per page using a local VLM (Qwen3-VL 8B). Features cross-page duplicate detection, checkpoint/resume for large batches, 4x parallel speedup, and consolidated Excel + JSON + Markdown exports. Integrates Mem0 — the system learns from corrections and gets smarter over time.

**Stack:** `VLM (Qwen3-VL)` `LangGraph` `Mem0` `OpenCV` `FastAPI` `Celery`

[![View Project](https://img.shields.io/badge/View_Project-FF6B6B?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Rayyan9477/Agentic-Document-Extraction-PDF)

#### 🤖 **AutoApply AI**
Job applications are repetitive — same forms, same clicks, hundreds of times. Built a full-stack AI platform (FastAPI + React + Redis) that discovers jobs, scores resumes against postings using FAISS vector matching, tailors documents via LLM, and submits applications through Playwright browser automation. Features a human-in-the-loop review workflow, batch processing queue, real-time WebSocket progress tracking, ATS scoring engine, and analytics dashboard. Supports OpenAI, Groq, and Gemini via LiteLLM routing.

**Stack:** `FastAPI` `React` `Playwright` `Browser Use` `Redis` `LiteLLM` `FAISS`

[![View Project](https://img.shields.io/badge/View_Project-FF6B6B?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Rayyan9477/AutoApply-AI-Agentic-Browser-Automation-for-Job-Search)

#### 📈 **MLOps Pipeline — USD Volatility Forecasting**
A prediction model is useless if it silently goes stale. Built a full production ML system that fetches live EUR/USD forex data, engineers 33 features, and retrains automatically every 2 hours via Airflow. Serves predictions through FastAPI with real-time drift detection on every request. Full observability: Prometheus metrics (latency P95/P99, drift ratio), Grafana dashboards with 13 alert rules, and MLflow experiment tracking. Runs as an 8-service Docker Compose stack with DVC data versioning, 5 CI/CD workflows, and 37 unit tests.

**Stack:** `Airflow` `Grafana` `Prometheus` `MLflow` `Docker` `DVC` `FastAPI`

[![View Project](https://img.shields.io/badge/View_Project-FF6B6B?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Rayyan9477/MLOps-Pipeline-for-USD-Forecasting)