Post-Doctoral Research Visit F/M Trait-Based Species Identification via Knowledge Extraction and Weakly Supervised Learning

Inria is the French National Institute for Research in Digital Science, of which the Inria Côte d'Azur University Center is a part. With strong expertise in computer science and applied mathematics, the research projects of the Inria Côte d'Azur University Center cover all aspects of digital science and technology and generate innovation. Based mainly in Sophia Antipolis, but also in Nice and Montpellier, it brings together 47 research teams and nine support services. It is active in the fields of artificial intelligence, data science, IT system security, robotics, network engineering, natural risk prevention, ecological transition, digital biology, computational neuroscience, health data, and more. The Inria Center at Université Côte d'Azur is a major player in terms of scientific excellence, thanks to the results it has achieved and its collaborations at both European and international level.

Automatic species identification from photographs is central to modern biodiversity monitoring, but current operational systems (Pl@ntNet, iNaturalist, Merlin Photo ID) rely on black-box deep learning models that lack interpretable internal structure and degrade sharply on rare, previously unseen, or out-of-distribution species. Human experts, by contrast, identify unfamiliar specimens through explicit reasoning over morphological traits: structured, interpretable descriptors such as leaf shape, beak curvature, or wing pattern.

eTaxonomist is an ANR JCJC project (2026 to 2030) that aims to close this gap by developing computer vision methods that emulate expert, trait-based reasoning. The project consists of three work packages: constructing structured trait knowledge bases from expert sources (WP1), grounding this structured knowledge visually in images (WP2), and integrating both into an interpretable, zero-shot reasoning framework (WP3). The approach will be validated across three case studies of increasing taxonomic breadth: agriculturally important insects of France, birds, and plants worldwide.

The project will be under the supervision of Diego Marcos (Inria), Alexis Joly (Inria, Pl@ntNet co-founder) and Zeynep Akata (TU Munich) and will count with the support of expert taxonomists accross all taxonomic groups  and with the Pl@ntNet platform.

The postdoctoral researcher will contribute primarily to WP1 (creation of domain knowledge bases) and WP2 (visually grounded trait-based descriptions). The position centers on building automated pipelines that turn unstructured expert knowledge (floras, handbooks, identification guides, and web-sourced descriptions) into structured, machine-readable knowledge bases of species-trait relationships, and on contributing to the computer vision methods that ground these traits in images.

• Assemble and curate heterogeneous textual corpora of morphological species descriptions across plants, insects, and birds;
• Design and evaluate LLM-based pipelines for domain ontology construction, including in-context learning and self-supervised fine-tuning strategies adapted to specialized taxonomic vocabulary;
• Populate the knowledge base with structured (class, entity, quality, value) tuples and comparative/hypergraph facts, combining LLM-based extraction with existing structured databases (TRY, GBIF, eBird, EOL TraitBank);
• Contribute to weakly supervised computer vision methods for part-aware representation learning and trait prediction from images, in collaboration with the PhD student in the same project;
• Set up and run evaluation protocols (precision/recall against expert-curated gold standards, knowledge graph consistency, downstream zero-shot utility) in collaboration with domain expert partners;
• Contribute to publications in top computer science conferences and open-source releases;

Required:

• PhD in Natural Language Processing, Knowledge Representation, Computer Vision, or a closely related area of Machine Learning;
• Strong programming skills (Python) and experience with deep learning frameworks (PyTorch);
• Experience with large language models (prompting, in-context learning, and/or fine-tuning);
• Ability to work independently and collaboratively within an interdisciplinary, multi-partner consortium;
• A strong track record of publications in top computer science venues;
• Good written and spoken English.

Appreciated:

• Experience with knowledge graphs, ontologies, or structured knowledge extraction;
• Experience with vision-language models (e.g., CLIP) or weakly supervised visual representation learning;
• Interest in or prior experience with biodiversity, ecology, or natural history applications;
• Experience with large-scale HPC environments (e.g., Jean Zay);

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

Gross Salary: 2788 € per month