Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hello! I'm Etienne Ferrandi, a Lyon-based AI Engineer focused on turning research into practical, deployed LLM-powered solutions. I enjoy extracting structured knowledge from large document collections, building RAG pipelines, and deploying LLMs in production on AWS Bedrock and local GPUs. I collaborate with researchers and civil servants to create augmented, reliable answers and semantic graphs that help people navigate complex information. In my work, I blend data engineering, NLP, and software development to deliver usable tools for real-world challenges.…Hello! I'm Etienne Ferrandi, a Lyon-based AI Engineer focused on turning research into practical, deployed LLM-powered solutions. I enjoy extracting structured knowledge from large document collections, building RAG pipelines, and deploying LLMs in production on AWS Bedrock and local GPUs. I collaborate with researchers and civil servants to create augmented, reliable answers and semantic graphs that help people navigate complex information. In my work, I blend data engineering, NLP, and software development to deliver usable tools for real-world challenges.

Etienne Ferrandi

AI Engineer, Data Scientist, Full Stack Developer, +2





Hello! I'm Etienne Ferrandi, a Lyon-based AI Engineer focused on turning research into practical, deployed LLM-powered solutions. I enjoy extracting structured knowledge from large document collections, building RAG pipelines, and deploying LLMs in production on AWS Bedrock and local GPUs. I collaborate with researchers and civil servants to create augmented, reliable answers and semantic graphs that help people navigate complex information. In my work, I blend data engineering, NLP, and software development to deliver usable tools for real-world challenges.…Hello! I'm Etienne Ferrandi, a Lyon-based AI Engineer focused on turning research into practical, deployed LLM-powered solutions. I enjoy extracting structured knowledge from large document collections, building RAG pipelines, and deploying LLMs in production on AWS Bedrock and local GPUs. I collaborate with researchers and civil servants to create augmented, reliable answers and semantic graphs that help people navigate complex information. In my work, I blend data engineering, NLP, and software development to deliver usable tools for real-world challenges.

Available to hire

Hello! I’m Etienne Ferrandi, a Lyon-based AI Engineer focused on turning research into practical, deployed LLM-powered solutions. I enjoy extracting structured knowledge from large document collections, building RAG pipelines, and deploying LLMs in production on AWS Bedrock and local GPUs.

I collaborate with researchers and civil servants to create augmented, reliable answers and semantic graphs that help people navigate complex information. In my work, I blend data engineering, NLP, and software development to deliver usable tools for real-world challenges.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

French

Fluent

Work Experience

AI Engineer at SMADE

June 1, 2025 - Present

Building a conversational agent with langgraph / langchain on a medical kit tracking software; RAG with qdrant; Cloud provider for LLMs: Bedrock; Deployment on AWS: Bedrock Agentcore

LLM Engineer at Persée (ENS de Lyon, CNRS)

June 1, 2024 - November 1, 2025

Extraction of structured knowledge from a large quantity of documents; XML/TEI data extraction; Data mining to identify unstructured bibliographic data with quantized LLMs: inference (vllm) on local GPUs from ENS Lyon (no cloud provider used); Structuration of those messy data via RAG (qdrant KB) and constraint generation (Pydantic); Fine-tuning of different llms: encoder-decoder mt5, decoder-only llama 3.1 8B (transformers)

Consultant Data at Datactivist

May 1, 2023 - May 1, 2024

Building a RAG agent: Albert API (chunking, embedding in a vector DB of XML data, use of different llms to provide augmented answers to public servants); Extraction of bibliographic unstructured data on 20th century archives of the Historical Service of the Ministry of Defence with SOTA OCR/HTR models; generation of XML/EAD encodings of archive collection inventories; Project management support for the implementation of a semantic graph tool for research data for the IRD

Développeur Full Stack at Janalis

September 1, 2022 - May 1, 2023

Redesign of an intranet for Sources Chrétiennes; Upgrade to the latest version (PHP 8.1); Migration of the MySQL database; Update of the biblindex website; Creation of the user journey; Definition of a Twig template for sending emails; Configuration of user permissions in the EasyAdmin interface

Ingénieur d’études at IRHT - Institut de recherche et d'histoire des textes

June 1, 2021 - December 1, 2021

Technical translation of the business requirements of researchers for the SourcEncyMe project; Encoding raw texts in XML/TEI; Deep learning from scratch (named entity recognition, NER)