Data scientist & AI Engineer
NLP · LLM · RAG · Machine learning · Audio & speech processing
I design and deploy AI applications, from scoping to production. Twenty-two years of engineering and solid hands-on data practice. I bring technical rigour, domain grounding, and a pedagogical sensibility.
A few projects that summarise my practice:
An automated data pipeline for the Metropolis of Lyon that retrieves, extracts, and compares public facility opening hours using semantic filtering and large language models.
Python benchmarking framework for text embedding models: grid search over chunking strategies and similarity metrics, with textual heatmap and embedding space visualizations.
Local Python audio transcription pipeline with speaker diarization, usable in real time (microphone) or on file. Works offline after initial model download.
Interactive visualizations for exploring statistical and machine learning concepts.
A command-line utility for low-level validation, automated repair, audio duplicate detection, and ReplayGain normalization of FLAC files.
Co-design and facilitation of AI training workshops, and production of pedagogical resources (prompting booklet, facilitator guide) for employees of the Metropolis of Lyon.
Below you can find my various professional networks, my contact information, and my interactive resume.