> whoami

Abdel TouatiAI Engineer · Generative AI & RAG

I design AI systems that understand your documents and automate your processes — deployable 100% on-premise, for companies that value data sovereignty.

{ }

code + data

> cat ~/approach.md

My Approach

Expert in RAG architectures and multi-agent systems, I design LLM solutions that integrate with your business processes while ensuring security and compliance.

> Principles

100% on-premise AI (Ollama, vLLM) — your data stays with you

GDPR & AI Act compliance built-in from design

Granular access control (RBAC/ACL) on documents and AI responses

Full auditability (logs, traceability, explainability)

> What I Do

Hybrid RAG systems (semantic + lexical search)

Orchestrated AI agents (LangGraph, LangChain)

Secure document ingestion pipelines

On-premise LLM integration (Ollama, vLLM)

> I support projects from POC to deployment, in dialogue with tech, legal and business teams.

> ls ~/projects --featured

Recent projects

open sourcev1.11

RAGnarok-AI

Local-first RAG evaluation framework with a CI/CD GitHub Action. 20 adapters, Medical Mode, ~24K queries/sec.

#RAG#LLM#GitHub Action

AI / LLMOps2026

On-premise AI Assistant — Legal Platform

Freelance engagement: design and production rollout of the AI assistant of a legal case management platform, 100% on-premise on a server without GPU.

#Hybrid RAG#Agents#FastAPI

AI Project2025

Space Coders Agency

AI-driven EdTech platform with a multi-agent architecture, designed to support learners and teaching teams.

#LangGraph#RAG#Multi-agent

> cat ~/.tech_stack

Technologies

Python

95%

SQL

85%

TypeScript

75%

JavaScript

70%

Bash

70%

LangChain / LangGraph

90%

Scikit-Learn

85%

TensorFlow

70%