Call for Postdoctoral Researcher - Industrial Document Intelligence with LLM Research and Engineering - Paris, France

Paris, France

Project: DEXTER4LLM
Contract duration: 18 months
Dates: 01/06/2026 to 31/12/2027
Work location: Paris (France)

Context: DEXTER4LLM is a collaborative R&D project under France-2023 aiming to build a sovereign-AI solution for structured extraction and automated analysis of complex industrial geographic documents (text, tables, figures, diagrams, plans, handwritten notes, etc.) [1], validated on high-impact industrial use cases (nuclear/mining & process engineering).

ECE leads the LLM Engineering (24 months) lot focusing on adaptation, optimization, and model merging to deliver frugal, high-performing geo-spatial (language / vision / multimodal) models for industrial workloads.

Mission: The post-doctoral will contribute to the scientific and engineering backbone, including:

• Geo-spatial semantic embedding (multimodal)
• Document extraction and knowledge integration (knowledge graph / ontology).
• Domain adaptation / fine-tuning and model optimization.
• Model merging research & engineering: implement and evaluate merging recipes (e.g., DARE-TIES, SLERP-style interpolation, novel alternatives.
• Benchmarking & metrics: accuracy/F1 for extraction, faithfulness (GraphRAG-style evaluation), and measurable frugality targets (compute reduction with environmental monitoring).
• Sustainability-aware evaluation.
• Research outputs: contribute to publications, open science where possible, and tech transfer with consortium partners.

The postdoctoral will work with the ECE team (Intelligence Lab) and in a consortium including major French enterprise.

Candidate profile (required):

• PhD in Computer Science with ML/NLP/AI/GeoAI (or close field).
• Strong Python + deep learning experience (PyTorch ecosystem).
• Solid understanding of LLM training/fine-tuning (data pipelines, evaluation, failure modes).
• Ability to produce reproducible research (experiment tracking, clean repo practices) and produce high-impact research in Q1 journals / A level conference venues.

Contract & benefits:

• 18-month postdoctoral contract (French research contract).
• Competitive salary according to experience and applicable French scales.
• Access to computing resources (sovereign cloud + local infrastructure as applicable).

How to apply:

Please prepare a single PDF including:

• CV (with publications)
• Short cover letter (1-2 pages) describing fit with LLM research
• PhD thesis title with defense date
• Contact details of 3 referees (or reference letters if available)
• (Optional) links to code, preprints, demos

*Applications are evaluated on a rolling basis until the position is filled.*

Contact Details:

Bikram Pratim BHUYAN, Researcher and Head of MSc Data and AI, ECE, bpbhuyan@ece.fr

AKNIN Patrice, Vice Dean, ECE, paknin@ece.fr

References:

1. Ke, W., Zheng, Y., Li, Y., Xu, H., Nie, D., Wang, P., & He, Y. (2025). Large language models in document intelligence: A comprehensive survey, recent advances, challenges, and future trends. ACM Transactions on Information Systems, 44(1), 1-64.