I design and build retrieval systems, LLM integrations, and the data pipelines that keep them honest. Engineering partnerships with companies and product teams that need AI to actually deliver.
What I do
Retrieval and LLM systems engineered for accuracy, latency, and cost. Built to stand up under real traffic, not benchmark demos.
The ingestion, transformation, and evaluation layers your AI products rely on. Reproducible, observable, designed to outlive their first model.
From open question to working prototype in weeks. I help teams de-risk AI ideas before they become roadmap commitments.
Projects
Trained and evaluated YOLOv5, YOLOv6, YOLOv8, YOLOv10, YOLOv11, and DETR models for pothole detection using custom datasets. Implemented data augmentation (Mosaic, MixUp, Geometric transforms). Dashboard and visualizations built with Tableau.
A geospatial and semantic search recommender system for eco-friendly hotels in Paris. Combines RoBERTa-based similarity with Haversine distance to suggest hotels based on sustainability and user intent. Built with FastAPI, async architecture, and deployed in Docker.
Transforms unstructured customer reviews into satisfaction scores using advanced NLP techniques. Models include TF-IDF, Neural Networks, RoBERTa, and LLaMA 3.2 fine-tuned with LoRA. Includes SHAP-based interpretability and a public Streamlit app.
A full-stack Product Lifecycle Management platform for a yogurt company. Features BOM tracking, recipe management, supplier/customer relationship tracking, Solidworks integration, invoice handling, and project dashboards. Centralized with MongoDB and role-based access.
A full-stack AI platform that ingests unstructured documents and autonomously generates semantic Neo4j Knowledge Graphs. Built with a high-density Next.js SaaS architecture and a FastAPI backend, the platform features a native GraphRAG chat engine powered by LangChain. It supports hot-swappable LLM execution, allowing users to seamlessly pivot between lightning-fast cloud models (Google Gemini) and highly private local hardware execution (Ollama).
What people say
He took ownership of complex tasks and delivered with both rigor and creativity, a rare blend of research-oriented mindset and engineering discipline.
PhD · Data Scientist & AI Engineer · Astek
I taught Ahmed during his preparatory cycle at Ecole Polytechnique Internationale: disciplined, autonomous, and gifted in problem-solving.
Computer Science Teacher · Polytech Intl
Ahmed is a talented developer with solid skills across security, development, and networking, which he puts to use effectively to advance whatever project is entrusted to him.
iOS Developer · Swift & SwiftUI · Qovoltis
About
I'm an AI engineer trained at ESILV (Data & AI, M.Eng. equivalent), based in Paris. Most of my work sits at the intersection of large language models, retrieval, and the data pipelines that keep them accurate over time.
I've shipped LLM evaluation systems and predictive models inside an asset manager, an engineering consultancy, and an EV-charging product. Across those, the same pattern: define the outcome clearly, choose the smallest system that delivers it, and instrument it so nothing degrades quietly.
Experience
Building AI agents and RAG / GraphRAG pipelines end-to-end, from prompt architecture and evaluation through to production deployment.
Designed and evaluated an LLM-driven CV–job matching system across DeepSeek, Gemma, LLaMA, Mistral and Phi. Built the inference and evaluation pipelines, and co-authored a research paper on hybrid explainable matching (defended 18.5/20).
Built predictive models for corporate-issuer rating changes and default probabilities, with temporal feature engineering and class-imbalance handling. Delivered an explainable AI tool (SHAP/LIME) used by analysts on simulated investment pipelines from 2009 to 2024.
Shipped a cross-platform Flutter app for configuring EV charging stations: QR scanning, hotspot pairing, multilingual UI. Reduced hotline calls by 80%, ran hardware testing across embedded and UI teams.
Stack
Education
Integrated Preparatory Cycle, Engineering Programme · Computer Science
Get in touch
I take on a small number of engagements at a time. If you're shipping AI features and want a thoughtful technical partner, send a note. A few sentences on the problem is all I need to tell whether I can help.