Looking for a job

benoist l

@benoistl

Message

I investigate data quality and build reliable Data & AI pipelines with SQL and Python.

France

Message

At the French National Audiovisual Institute (INA), I investigate data anomalies with SQL and Python and improve the quality of media transcription and reference data across Data & AI projects.

I map end-to-end data flows across the data.ina.fr ecosystem, translate business rules into technical requirements, and work with engineers, data scientists, developers, and business users through testing and validation.

I built a Python training-data pipeline for a BERT-based named-entity disambiguation model and automated integration and regression testing with JMeter and Jenkins, reducing control time by more than 50%. I also designed YUMMY, a sustainable recipe recommendation MVP using Python, Airflow, dbt, DuckDB, FastAPI, and a Bronze/Silver/Gold data architecture.

Experience

Work history, roles, and key accomplishments

Data Project Officer

Institut national de l’audiovisuel (INA)

Jan 2023 - Jan 2026 (3 years)

Analyzed datasets using SQL and Python to investigate anomalies and support corrective actions across Data & AI projects. Performed data quality checks and mapped end-to-end data flows, contributing to reliable downstream processing and data delivery.

SQL Python Data Quality Investigation NLP BERT Data Pipelines Automation JMeter Jenkins Dagster CI CD Git Docker Helm

Data & AI Project

YUMMY – Sustainable Recipe Recommendation Platform

Designed an end-to-end Data MVP combining recipe, seasonality, and agricultural production datasets to generate personalized and sustainability-oriented recipe recommendations. Built data ingestion, cleaning, matching, and quality-control workflows to reconcile heterogeneous ingredient and agricultural data.