# Youssef Alouani

Source: https://www.alouaniyoussef.com/

**I build AI that works on real data in production, and keeps that data safe. AI engineer with a backend foundation: RAG and MCP over private data, Saudi-dialect speech, recommendations and privacy-aware assistants, evaluated before they ship.**

Casablanca-based AI engineer with a backend foundation: RAG, MCP, speech and privacy-aware assistants that work on real data in production.

## What I build

### Agentic systems & AI harnesses

RAG pipelines with an MCP server as the retriever, and assistants that act with the user's own permissions, redact personal data and ask before they write.

### NLP / NLU

Public chatbots on Botpress, Rasa and an in-house engine, from the backend and chat widgets to their security, plus intent and entity extraction tuned per client across Arabic, French and Darija.

### ML / DL & speech

Whisper large-v3 fine-tuned for Saudi-dialect calls, from audio preparation to evaluation, serving live transcripts and voice agents.

### Recommendation systems

Dish and drink pairings, meal-completion promos and event-based dynamic pricing, built on one menu data model.

### Data pipelines & ETL

Pipelines that collect, clean, extract into type-safe LLM schemas and load: job ingestion, call-recording pipelines and signed server-side CAPI events.

### Backend & platform

Multi-tenant SaaS with isolated data and identity per tenant, Kafka and RabbitMQ messaging, real time over WebSockets and SSE, Keycloak, and migrations to Kubernetes.

## Featured case studies

- [Osoul platform](https://www.alouaniyoussef.com/projects/osoul.md): Revenue as a Service for fine dining. A multi-tenant SaaS that captures the data restaurants usually lose and turns it into revenue KPIs.
- [Saudi-dialect speech-to-text](https://www.alouaniyoussef.com/projects/saudi-stt.md): Whisper large-v3 fine-tuned for Saudi dialect, with an audio pipeline for WhatsApp and Asterisk calls, behind live transcripts and tool-using voice agents.
- [Customer Voice: RAG pipeline with an MCP retriever](https://www.alouaniyoussef.com/projects/customer-voice.md): A RAG pipeline over structured data, documents and customer interactions, with an MCP server as its main retriever and auth, privacy and retention built in.

## Clients I have worked for

### Government and public institutions

- HRSD (Ministry of Human Resources and Social Development)
- King Saud Medical City

### Banks and insurers

- Saudi National Bank (SNB)
- Crédit du Maroc (CDM)
- SanlamAllianz
- AtlantaSanad

### International and hospitality groups

- Hertz Morocco
- Barceló Group
- Atlas Group

### Growth and technology companies

- YouCan
- CityClub
- Tahreez

## Elsewhere

- Schedule a call (Google Meet): https://calendar.app.google/ru99z5cCrAbbu8LP9
- Email: hello@alouaniyoussef.com
- GitHub: https://github.com/alouani-youssef
- LinkedIn: https://www.linkedin.com/in/alouani-youssef
- Résumé (JSON Resume): https://www.alouaniyoussef.com/resume.json
