Turning raw data into powerful engines. 15+ years building data infrastructure that actually scales.
I design and build robust data systems — from large-scale ETL/ELT pipelines and intelligent web scrapers to AI-powered applications in production. My work sits at the intersection of data engineering, full-stack development, and applied AI.
- 📦 Architecting ETL/ELT pipelines at scale
- 🕷️ Web scraping & intelligent data collection
- 📊 Enterprise-grade reporting systems used by millions
- 🤖 Fine-tuning LLMs and building AI-powered products
- 🌐 Full-stack development with PHP, Python & modern tooling
| Project | Description | Stack |
|---|---|---|
| Offres-Travail.com 🏆 | Largest job listings aggregator in France by volume | Big Data, Search, Automation |
| Pylon-Monitor.com | Standalone WiFi device for remote Pylontech battery monitoring — JSON API, MQTT & native Home Assistant integration | IoT, Hardware, API |
| Cables-Solaires.com 🏆 | E-commerce for solar battery cables | E-commerce |
| Free-LLM.com ✨ | World directory of 40+ free LLM API providers | Directory, Community |
| SummarizeAPI.com ✨ | AI text summarization REST API, multilingual | NLP, LLM, API |
| CategorizeAPI.com ✨ | AI text/content categorization REST API, multi-level classification | NLP, LLM, API |
| PDF-Summarize.com ✨ | Free AI-powered PDF summarizer, 15+ languages | NLP, Document Analysis |
| TextPerfector.com ✨ | AI-powered writing & grammar correction platform | NLP, LLM |
| TheBookee.net | ElasticSearch PDF engine with AI-generated summaries | OCR, ML, Search |
| Similars.net | Semantic clustering engine indexing 14M+ websites | Big Data, NLP |
| Rankeez.com | Real-time SEO analytics with predictive ML on 32M+ sites | Predictive ML, Big Data |
| Lizarder.com | Deep learning translation engine, 40+ languages, 50M+ translations | Deep Learning, NLP |
| TrADuck.com ✨ | High-accuracy AI translation for 35+ languages | AI, NLP |
| XeConvert.com | Currency converter with predictive analytics, 170+ currencies | FinTech, Real-time |
| L-Actualite.com ✨ | AI-curated French news with trend detection | IA, Big Data, NLP |
| Langs.education | Adaptive AI language learning platform | EdTech, NLP |
| StatMemory.com | Full web analytics: traffic, SEO, WHOIS, hosting | Data Mining, Analytics |
| NejibTech.com | One of the only French stores fully dedicated to AZERTY French-Arabic bilingual keyboards & mice | E-commerce, Niche Market |
| Latest-Headlines.com ✨ | AI-curated US news platform with real-time trend analysis | AI, Content Generation, News |
| Tunisie.me ✨ | Tunisian news portal using ML to personalize content by reader interest | ML, Data Processing, News |
| ResterConnecte.com ✨ | Daily educational content platform (health, cooking, tech…), AI-generated & auto-validated articles | Content Generation, Automation |
| Esperance-De-Tunis.com ✨ | Sports platform with a custom ML model for real-time performance analytics, trained on 15+ years of data | Custom ML, Real-time Analytics |
| Linux-Alternative.com | Recommendation engine for Linux alternatives to Windows software | Recommendation System, ML |
| FrContext.com ✨ | Free multilingual encyclopedia, 14 languages, several hundred thousand entries | Encyclopedia, Multilingual, Big Data |
| PDF-Downloads.net | Search engine specialized in educational PDF documents | Search Engine, Education |
| Tarjma.com | Fast, simple online translation service | Translation |
| Budokan Academy | Sports club platform, fully dynamic no-code backoffice, news/Telegram API, real-time stats & scheduling (non-profit judo club, not a personal business) | Full-Stack, PHP, Automation |
A family of standalone AI-powered REST APIs and micro-SaaS tools, each shipping its own docs, pricing and developer-first integration — the applied side of the data/AI work above.
| API product | What it does |
|---|---|
| SummarizeAPI.com | Multilingual AI text summarization, REST endpoint |
| CategorizeAPI.com | AI text/content classification & categorization, REST endpoint |
| TextPerfector.com | AI grammar & writing correction |
| TrADuck.com | AI translation, 35+ languages |
| PDF-Summarize.com | AI PDF summarization, 15+ languages |
| Similars.net | Website-similarity API backed by a 14M+ site semantic index |
| Rankeez.com | SEO ranking analytics API with predictive ML |
| Free-LLM.com | Directory & comparison API for 40+ free LLM providers |
Data & Pipelines
Web Scraping SAS Databricks Apache Spark Elasticsearch Airflow Pandas Anaplan
Artificial Intelligence
TensorFlow PyTorch Transformers LangChain Hugging Face OpenAI API
Databases
PostgreSQL MongoDB Redis ClickHouse Pinecone Weaviate
Cloud & DevOps
AWS GCP Docker Kubernetes Terraform GitHub Actions Axway
Languages
Python PHP SQL JavaScript
15+ years of experience
27+ active projects
10M+ users reached
50+ technologies mastered
170+ currencies tracked in real-time
50M+ translations processed
32M+ websites analyzed daily
14M+ sites indexed in semantic search
I'm open to data engineering missions, AI consulting, full-stack contracts, and strategic collaborations.
- 🌐 nejib.com
- 💼 linkedin.com/in/nejib1
- 📍 Paris, France
- 📞 +33 6 42 53 80 35
"Data is the raw material. Architecture is the craft. Impact is the goal."