About Jean-Baptiste
Ingénieur Intelligence Artificielle
Quelques informations sur moi
- Je suis ingénieur IA. Expérience en NLP (LLM) et Computer Vision. Expert Python.
- 8 ans d'expériences
- Je parle Anglais couramment
Mes références
Engine, Acolad, Aive, Admo.tv
Pourquoi faire appel à moi en qualité d'Ingénieur IA ?
- Je vous accompagne pour le diagnostic et l’identification des opportunités
- Je conçois des solutions IA de bout en bout : du prototypage à l'industrialisation
- Expert en développement Python, backend, API.
- Encadrement de profil junior
- Mise en place des bonnes pratiques de code (Coding Assistant : Claude Code, Open Code, CI/CDD, Typing, Revue de Code).
French
Native or bilingual
English
Fluent
Can work on-site
Montpellier (up to 50km), Paris (up to 10km), Marseille (up to 10km), Toulouse (up to 10km), Lyon (up to 10km)
Experience
- BCA ExpertiseAI EngineerNovember 2024 - April 2025 (5 months)Real time automatic car accident report generation from audio transcription.
- Built data extraction model based on LLM tailored for car accident report (guided decoding).
- Created synthetic data creation pipeline and custom score metric.
- Fine tuned LLM (Llama 3.1 8B) on json diff task.
- Deployed with sub second latency (TensorRT-LLM).
- Groupe ACOLADAI EngineerEDUCATION AND E-LEARNINGMarch 2024 - October 2024 (8 months)Paris, FranceHelped Acolad develop AI solutions for Machine Translation, Automatic Post-Editing and Quality Evaluation.
- Developed LLM prompt engineering and RAG for Machine Translation Post-Editing, reducing manual effort by 40%
- Train non-technical teams to use AI tools via the Orq AI collaboration platform.
- Built serverless GPU-powered backend on Modal for Automatic Post-Editing and Quality Evaluation simplifying deployment.
- AiveMachine Learning EngineerSOFTWARE PUBLISHINGSeptember 2020 - December 2023 (3 years and 4 months)Montpellier, FranceAive is an AI-assisted video editing platform, it automates post-production, intelligently adapting videos across all formats.
- Enhanced SOTA transcript topic segmentation of 44% via LLM prompt engineering and fine-tuning.
- Increase SOTA video scene detection of 20% with better model architecture and training.
- Built a rule-based black bar detection model, optimized with Numba.
- Developed a color palette detection model using k-means and color histograms.
- Trained models for place and scale video classification.
- Transitioned object-based cropping to machine learning saliency detection.
- Reengineered video OCR from PaddleOCR to PyTorch with improved text tracking.
- Built optimized video decoder and visualisation tool backed by PyAV and FFmpeg.
- Mentored team by building a repository for reproducible research with PyTorch Lightning, Weights & Biases, and Ray.
Recommendations
Be the first to recommend Jean-Baptiste
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
- Deep Learning SpecializationCoursea2017