Publisher
source

Inria

Postdoctoral Research Visit in Trait-Based Species Identification, Knowledge Extraction, and Weakly Supervised Learning Inria in France

Degree Level

Postdoc

Field of study

Computer Science

Funding

Full funding available

Deadline

Sep 30, 2026

Country flag

Country

France

University

Inria

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Keywords

Computer Science
Environmental Science
Information Technology
Biology
Natural Language Processing
Biodiversity
Computer Vision
Knowledge Representation
Large Language Models
ML

Suggested positions

About this position

Inria is recruiting a Post-Doctoral Research Visit for the eTaxonomist ANR JCJC project, based at the Inria Centre at Université Côte d’Azur in Montpellier, France. The project sits at the intersection of computer vision, natural language processing, knowledge representation, knowledge extraction, and weakly supervised learning, with a strong biodiversity and taxonomy application.

The research aims to improve automatic species identification from photographs by moving beyond black-box deep learning toward interpretable, trait-based reasoning. The postdoctoral researcher will mainly work on building structured knowledge bases from expert textual sources such as floras, handbooks, identification guides, and web descriptions, and on methods that ground morphological traits in images. The project spans plants, insects, and birds, and is validated through case studies in agriculturally important insects of France, birds, and plants worldwide.

Supervision is shared by Diego Marcos (Inria), Alexis Joly (Inria, Pl@ntNet co-founder), and Zeynep Akata (TU Munich), with support from expert taxonomists and the Pl@ntNet platform. The role includes assembling corpora, designing LLM-based ontology construction pipelines, extracting structured species-trait facts, integrating external databases such as TRY, GBIF, eBird, and EOL TraitBank, and contributing to part-aware visual representation learning and trait prediction.

Eligibility highlights: PhD or equivalent in NLP, knowledge representation, computer vision, or a related machine learning area; strong Python/PyTorch skills; experience with LLMs; strong publication record; good English. Helpful extras include knowledge graphs, ontologies, vision-language models, weakly supervised learning, biodiversity experience, and HPC familiarity.

Funding: fixed-term postdoctoral contract, 2 years, gross salary 2788 € per month, plus standard Inria benefits.

Deadline: 2026-09-30. Applications must be submitted online via the Inria job portal.

Funding details

Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.

How to apply

Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?