About Mohamed
I help companies leverage their data through tailored AI solutions. Whether you need an intelligent agent to automate part of your workflow or a machine learning model to predict key business outcomes, I can design, train, and deploy it efficiently.
My added value lies in combining strong technical expertise with a deep understanding of real-world business needs — ensuring each model is both accurate and usable in production.
I usually handle projects involving:
- Creation of AI chatbots or assistants powered by OpenAI and retrieval-augmented generation (RAG)
- Predictive modeling and time series forecasting
- Natural language processing and sentiment analysis
Arabic
Native or bilingual
French
Fluent
English
Fluent
German
Basic
Remote only
Primarily works remotely
Experience
- DeepkiData scientistREAL ESTATEJanuary 2026 - Today (6 months)Paris, France
- Designed and developed a customizable AI agent platform for internal use cases, enabling rapid deployment of task-specific agents across teams (leveraging tools such as Langfuse and Strands).
- Built a high-performance Retrieval-Augmented Generation (RAG) pipeline to extract structured energy-related data from unstructured and noisy audit PDFs, significantly improving data accessibility and processing efficiency.
- Implemented end-to-end observability and evaluation pipelines using Langfuse, enabling monitoring, debugging, and performance tracking of all agentic AI applications in production.
- Collaborated with cross-functional teams to integrate AI agents into real business workflows, ensuring scalability, reliability, and measurable impact.
- Auditoo (Station F)AI EngineerREAL ESTATEJuly 2025 - December 2025 (5 months)Paris, France
- Designed and evaluated LLM-based AI agents using Pydantic-AI for robust data validation, structured output generation, and systematic performance benchmarking.
- Improved agent precision to 80–100% on internal evaluation datasets, significantly increasing the reliability of structured data extraction for energy audit reports (DPE).
- Contributed to end-to-end product development, including a Python backend, Flask API services, and a React frontend, ensuring seamless integration of AI components into the application.
- Worked closely with the founding team to develop an AI-powered web application that transforms speech-based descriptions of housing characteristics into structured and compliant DPE reports.
Reviews
Recommendations
Be the first to recommend Mohamed
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Master of Engineering In Artificial IntelligenceCentraleSupélecArtificial intelligence
- Exchange Semester in Computer ScienceFaculdade de Engenharia da Universidade do Porto (FEUP)2025Exchange Semester in Computer Science
Certifications
- Advanced Learning AlgorithmsStanford University2024