I'm a Data Scientist and AI Engineer with a PhD in Automation, focused on building production-grade ML systems for Industry 4.0 environments. I don't just prototype — I ship things that run in the real world, on real data, under real constraints.
Currently leading AI & data initiatives at IME, where I architect data pipelines, deploy ML models, and orchestrate workflows with Apache Airflow. I build and maintain open-source Python and R packages, and I care deeply about clean APIs, solid documentation, and reproducibility.
- 🔬 Core expertise: statistical modeling, distribution fitting, anomaly detection, time-series, ETL pipelines
- 🤖 Working with: LLMs, Apache Airflow, ML pipelines, data engineering
- 📦 Publisher of Python & R packages used in production
- 🌍 Based in Tehran, Iran — building in the open
Languages
ML / Data
Infra & Orchestration
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| 🤖 local-sql-agent | Chat with your SQL database in plain English — fully local AI agent powered by Ollama, RAG-based schema retrieval, multi-database support | Python |  |
 |
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| 📊 py-distfit-pro | Production-grade statistical distribution fitting — 30 distributions, MLE/MoM/Quantile, Bootstrap CI, multilingual (EN/FA/DE) | Python |  |
 |
| 📊 distfitr | Statistical distribution fitting toolkit | R |  |
 |
| 🔍 missingly | Missing data detection & analysis | Python |  |
 |
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| ⚙️ apache_airflow_dags | Production-grade Apache Airflow DAG collection | Python |  |
 |
| 💰 MultiRateScrapper | Scrape Iranian financial rates (USD, gold, BTC, oil, stock index) from tgju.org into SQL Server | Python |  |
 |
| 📉 tgju-data-collector | Financial market data collector from tgju.org | Python |  |
 |
| 🏭 ice-data-collector | Scraper for ICE market data | Python |  |
 |
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| 🇮🇷 farsi-faker | Generate realistic fake Persian names for testing & development | Python |  |
 |
| 📈 daily-github-pulse | Discover GitHub's top trending repositories filtered by language, recency, and star activity | Python |  |
 |
| 🔑 password-generator | Secure CLI password generator with guaranteed complexity | Python |  |
 |
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| 🔒 v2ray-finder | Fetch, aggregate & filter free V2Ray/Xray configs from GitHub — supports vmess, vless, trojan, and shadowsocks with smart deduplication | Python |  |
 |
| 🌐 ShecanDNSSetter | Automatically switch Windows DNS to Shecan — bypasses internet filtering for Iranian users via Python and batch scripts | Python |  |
 |
| Project | Description | Lang | Stars | Forks |
|---|---|---|---|---|
| ⬇ smart-dl | Resilient multi-threaded YouTube & podcast downloader built for unstable networks & VPNs | Python |  |
 |
| 🎵 music-organizer | Auto-organize MP3 libraries via metadata lookup & audio fingerprinting — GUI + CLI, duplicate merge, dry-run support | Python |  |
 |
Open to collaboration on data science, ML tooling, LLMs, and open-source projects · alisadeghiaghili@gmail.com