AI/ML, automation and backend engineering for products and businesses that need more than another prototype.
Each number links to the case study behind it.
01Selected work
From a production LLM pipeline to distilled NLP models and replicated inference APIs. Every project is labelled for what it is: internship work, or academic projects.
Multilingual LLM lead pipeline
Messages prospects send on WhatsApp, Instagram or Messenger, in French, English or Darija, are turned into structured CRM leads automatically.
Toxic speech detection in Moroccan Darija
A multi-label NLP system that detects toxic speech in Moroccan Darija, with a large teacher model distilled into a compact, faster student.
Early detection of viral trends
A machine-learning system that predicts which keywords will go viral, from their very first minutes of activity.
Institutional web platform
Flights, hotels, transport, recruitment and public tenders, brought together in one platform for Morocco’s national airports authority.
Replicated inference API
A scalable inference API: a FastAPI model service replicated behind an Nginx gateway, with a versioned model registry.
Full-stack and academic projects, from my GitHub.
A layered .NET solution: an ASP.NET Core MVC web app for customers and a Windows Forms desktop app for administration, on an Entity Framework Core data layer.
Real-time monitoring of industrial machines with AI-based anomaly detection, live alerts and multi-level user access.
A mobile app with a REST back end for tracking a baby’s growth, milestones, nutrition, vaccinations and appointments.
02Services
A model is only useful once it’s part of a system people can rely on. I work across the whole of it: the model, the API around it, the data underneath, the automation that feeds it and the interface on top.
LLM integrations, structured extraction, NLP, model inference and intelligent applications.
Related case studies
Business workflows, lead processing, message automation, APIs, n8n and intelligent routing.
Related case studies
FastAPI, Flask, REST APIs, databases, authentication and scalable services.
Related case studies
React and TypeScript interfaces connected to real backend systems: dashboards, internal tools and AI-powered features.
Related case studies
03About
I’m Achraf Abderrazik, a final-year Software Engineering student at EMSI, specialising in Artificial Intelligence & Data Science.
While I complete my engineering degree, my professional focus is AI / ML engineering, AI automation, and backend & intelligent systems.
In both of my internships I was the sole developer, from design to production: first AeroManager for ONDA, Morocco’s national airports authority, then a multilingual LLM pipeline for a real-estate agency in Marrakech.
Jul – Aug 2026 · 9 weeks
AI Engineering Intern · Sole developerMarrakech
Designed and deployed to production a multilingual LLM pipeline that turns WhatsApp, Instagram and Messenger conversations into structured CRM leads.
Jul – Aug 2025 · 1 month
Software Engineering Intern · Sole developerMarrakech
Built AeroManager, an institutional web platform covering flights, hotels, transport, recruitment and public tenders, on a React SPA and a Flask REST API with role-based access.
04Stack
Grouped by where they sit in a system, from the model down to the infrastructure. Everything listed appears in my CV or public repositories.
05Contact
Tell me what you’re trying to build, automate or improve. I’ll come back with clear next steps.