R&D Engineer - AI & Tabular Data (M/F)

Dassault Systèmes, the 3DEXPERIENCE company, is an "accelerator of human progress." It offers companies and individuals collaborative virtual environments that allow them to imagine more sustainable innovations. By developing a virtual twin of the real world, thanks to the 3DEXPERIENCE platform and its applications, Dassault Systèmes empowers its customers to push the boundaries of innovation, learning, and production. Dassault Systèmes' 20,000 employees work to create value for our 270,000 customers of all sizes, in all industries, in more than 140 countries. For more information, visit our site www.3ds.com/frVous you will join the ENOVIA R&D Configurable Sales Experience (CPQ) department, within the team responsible for configurable product and portfolio management applications. The team notably develops ENOVIA Model Definition, a configuration management application, as well as an AI capability for AURA aimed at assisting the generation of configurable product models (variability, rules, and configurations) from a business description expressed in natural language.

In this context, you will explore the combination of Large Language Models (LLM) and Tabular Foundation Models (TFM) in order to accelerate the creation of new product configuration models while taking into account the data specific to each customer environment.

Your tasks You will be involved in:

• State of the art - studying Tabular Foundation Models such as TabPFNv2 and TabICL and analyzing their applicability to product configuration issues.
• Dataset construction - creating a representative structured dataset integrating configurable variants, rules, and bills of materials, from synthetic data or public examples.
• AI pipeline development - combining the interpretation of a business description by an LLM with the search for similar existing models.
• Generation of configurable models - automatically producing proposals for variability structures, rules, and reference configurations.
• TFM experimentation - studying the use of tabular models capable of generalizing from structured data provided in context.
• Evaluation - qualitatively and quantitatively measuring the relevance of the generated proposals.

Your qualifications

• You are preparing a Master's degree (Bac+5), from an engineering school or University Master's, with a specialization in AI-oriented software development.
• You have good knowledge of Python.
• You master the fundamentals of Machine Learning, notably Transformers and in-context learning.
• You are interested in structured data modeling and product configuration.
• You are partially familiar with the following tools and libraries: Pandas, NumPy, Scikit-learn, PyTorch, Hugging Face Transformers, LangChain and LangGraph.
• You possess foundations in NLP, LLM and generative AI.
• You will be required to work with an international team; proficiency in English is essential.

Joining us also means Integrating a scientific company at the heart of technological innovation, driven by strong growth for more than 40 years.

Main advantages and benefits:

• Multicultural environment
• Friendly working environment focused on well-being and health (gym & music rooms, concierge services.)
• Commitment to diversity and inclusion
• Dynamic career development policy: training plan, internal mobility, etc.