For an AI, ML or Data Engineering role
AI Engineer · GenAI Engineer · ML Engineer · Data Engineer · NLP Engineer
In 30 seconds
- 01Six months in industry on information extraction with self-hosted LLMs, on L40S / H100 GPUs and SLURM.
- 02An evaluation that measures attribution to the right objects, not just how good answers look.
- 03First author of a paper on RAG-based tailoring of risk reports (INFORSID 2026).
- 04Data pipelines with quality indicators, from object storage to partitioned tables.
Work, in the order that matters for this role
TotalEnergies OneTech · DataLab, Pau
The right value, for the right object: LLM extraction from industrial reports
Evaluated prototype, candidate for integration
CETIC · NLP, GenAI and cybersecurity
RiskTailor: one risk report, one rendition per reader
Published research — INFORSID 2026
MSc DataScale · joint project with Youcef Bouagada
Rules and an LLM that check each other: extracting a verifiable knowledge graph
Academic project — 50-sentence corpus
MSc DataScale · data integration and quality
Measuring quality before promising it: 38 indicators on energy data
Academic project
Data engineering project · simulated scenario
An open-source, AWS-style data lake, from raw object to partitioned table
Simulated volume — not a measured production throughput
Most relevant experience
04 — 09 · 2026
TotalEnergies OneTech · HPC Data Scientist / Data Engineer (MSc internship)
Metadata extraction with self-hosted LLMs on GPUs, with an evaluation that separates identifying objects from the quality of their attributes.
01 — 03 · 2026
CETIC · NLP & GenAI R&D, cybersecurity
RAG pipeline and FastAPI service tailoring a risk report to its reader; first author of RiskTailor (INFORSID 2026).
06 — 08 · 2024
CERIST · Video processing & computer vision
Video anomaly-detection pipeline: ingestion, features, CNNs and autoencoders, evaluation.
2022
Sonatrach · APCS · Data & enterprise applications
Oracle modelling and PL/SQL, an APEX application with row-level security; Odoo modules and SQL logistics reporting.
AI & GenAI
LLMs evaluated as systems, not demos.
- Structured extraction with self-hosted LLMs (vLLM, Pydantic)
- Two-level evaluation, error analysis, ClearML tracking
- RAG and reader-aware generation, served as an API
- Hybrid rules + LLM NLP validated by an ontology
CV · AI & Data profile
The current version is being finalised. Write to me: I'll send it the same day.