DZ-Stagiaire
The first step — where students, schools, and companies meet.
I build complete AI systems end to end — models, pipelines, and the interfaces around them. What you get isn't code; it's a working system and the results it produces in production.
I deliver production AI systems end to end — from model orchestration and retrieval pipelines to the interfaces people actually use. Two years turning ambiguous problems into systems that run, reason, and produce measurable results. I work where research meets reliability: experiments that must ship, and systems that must keep working long after they do.
Each step up the sequence — closer to the truth, heavier the systems entrusted to me.
Built an intranet IT intervention platform for 300+ Algérie Télécom employees, cutting average resolution time by ~40%. Delivered a real-time WebSocket dashboard with KPIs and per-department analytics, a Python/tkinter desktop widget compiled to .exe, email notifications, and Excel import/export with server-side validation. Handled intranet security: auth, upload validation, and file permissions.
Built and shipped full-stack apps and AI automation workflows for small clients. Wired together n8n pipelines, custom APIs, and LLM-powered agents to remove manual work. Delivered dashboards, scrapers, and notification systems end to end — running in production, not just demoed.
Three cards from the archive — each a system shipped, each a result delivered. Turn one to read the engineering behind it.
The first step — where students, schools, and companies meet.
A full-stack platform that streamlines the entire student internship lifecycle. Tracks applications, administrative approvals, and final evaluations in one workflow — replacing fragmented paperwork with a single, working system.
The guardian at the gate — permission middleware for AI agents.
Open-source middleware that gatekeeps every tool call an AI agent makes. YAML policies are enforced deterministically across 7 frameworks; pluggable LLM assistants escalate ambiguous decisions, and a context inspector catches indirect prompt injection. Policy is the floor — assistants can only tighten, never loosen.
The contract unseen — decoded, scored, and brought into the light.
A browser extension that reads the fine print no one reads. It ingests a site's Terms of Service, runs the clauses through a lightweight on-device transformer, and surfaces a privacy-risk score before you hand over your data. No cloud calls, no trackers — a quiet oracle for the small print. Currently in progress.
Three disciplines, practised in concert — the seer reads the surface, the savant forges the foundation, the oracle awakens the machine.
Interfaces with intent — fast, accessible, precise.
Foundations that endure — observable, deterministic, scalable.
Systems that reason — models, retrieval, and orchestrated intent.