Freelancer profile translated to English.

Description

I am an AI Engineer with experience in R&D on Speech Recognition (STT), Speaker Change Detection, and Computer Vision (object detection, pose estimation, segmentation).

Alongside my professional assignments, I develop personal projects combining LLMs, STT/TTS, and agentic workflows, transforming research into concrete applications. I blend industrial rigor with the agility of independent exploration to deliver production-ready systems.

🖼️ Computer Vision

Real-time development of detection, segmentation, and pose estimation for an aeronautics player (YOLO, ResNet, ViTs).
Design of object tracking pipelines for an insurance SaaS platform, analyzing car accidents in live video.

🎙️ Speech-to-Text & Text-to-Speech

Real-time embedded pilot transcription systems with speaker detection and diarization.
Expertise on pyannote, wav2vec, RNN-T for robust transcription.
Voice data generation via ElevenLabs and Coqui TTS.

🤖 LLMs & Automation

Internal GPT-like chatbots for system designers (Mistral).
Testing of embedded LLMs (Orange Pi) for checklist automation.
AI workflows with N8N, CrewAI, LangChain, OpenAI API.

⚡ What I bring

I integrate AI solutions ranging from constrained embedded systems to scalable SaaS platforms. From prototype to production application, I take your projects from 0 → 100:

🖥️ Frontend: Next.js, React, React Native, Streamlit, Dash

🗄️ Databases: SQL & NoSQL (MongoDB Atlas, Supabase, …)

☁️ Deployment: FastAPI, Docker, Cloud, embedded solutions

👉 If you are looking for an AI partner capable of rapid prototyping and delivering robust systems, let's build something exceptional.

Languages

French
Native or bilingual
Spanish
Fluent
Portuguese
Fluent
English
Fluent

Workplace preferences

Can work on-site

Paris (up to 50km)

Airbus,
Artificial Intelligence Engineer
November 2022 - February 2025 (2 years and 3 months)
Toulouse, France
Improvement of autonomous landing systems using computer vision and machine learning to optimize navigation accuracy and safety.
Design and deployment of a modular pipeline for object detection, pose estimation, and segmentation, applying MLOps best practices.
Optimization of embedded models through quantization, meeting real-time constraints on resource-limited systems.
Regular presentation of technical results and progress to stakeholders.
Development of speech recognition prototypes, from model training to hardware integration, to improve accessibility and human-machine interaction.
Conducting experiments with language models (LLMs), leading to AI tools such as chatbots. Collaboration with teams in France and Silicon Valley to innovate in AI-based navigation systems.
Text to speech artificial intelligence Computer Vision Image segmentation Pytorch
Aubay,
Computer Vision Intern
April 2022 - October 2022 (6 months)
Paris, France
Training of computer vision and machine learning algorithms, including RNNs and tracking models, to accurately detect accidents in dashcam videos.
Management and preprocessing of large volumes of embedded videos.
Development of a Dash application to demonstrate the system, from video loading to accident detection.
Collaboration with the project team and stakeholders.
Comprehensive presentation of results, methodology, and impacts during a final defense.
RNN Computer Vision OpenCV Dashboard SAAS
Enedis,
Data Scientist Intern
April 2021 - August 2021 (4 months)
Paris, France
Design of a simulation model based on Multi-Agent Systems (MAS) to analyze smart meter communication flows and optimize network performance.
Development of interactive dashboards with Dash to visualize simulation results and facilitate stakeholder decision-making.
Application of advanced data analysis techniques to improve simulation accuracy and reduce prediction errors.
20% reduction in error on performance indicators, demonstrating the model's reliability in near-real-world conditions.
Dash SMA Data science