Postdoc: Multimodal Representation Learning for Soil eDNA

CNRS - National Center for Scientific Research; France; On-site; EUR 36,000 - 48,000; Full time

Job summary

The postdoctoral researcher position at the Laboratoire d'Écologie Alpine (CNRS, Université Grenoble Alpes and Université Savoie Mont Blanc) invites applicants to develop representation learning methods linking soil community composition to environmental conditions using six markers and environmental data.

You will work within the BIOM team on multimodal data from ORCHAMP observatory and advance reproducible analyses.

Qualifications

• PhD in computational ecology, statistics, applied mathematics or artificial intelligence.
• Strong deep learning experience and knowledge of representation learning and ordination methods.
• Familiarity with eDNA and metabarcoding data is strongly recommended.
• Proficiency in Python; frameworks such as PyTorch or TensorFlow; scientific computing with large spatial datasets.
• Rigour in model validation and reproducibility; good level of scientific English.

Responsibilities

• Review literature on multimodal representation approaches and ordination methods in ecology.
• Set up reproducible analyses and assess available eDNA and environmental data.
• Link eDNA and environment marker by marker, comparing linear and non-linear approaches.
• Integrate multiple markers to study relationships and predict composition, trophic groups and diversity.
• Disseminate results through publications, presentations and open-source code.

Education

PhD in computational ecology, statistics, applied mathematics or artificial intelligence

Tools

Python

PyTorch

TensorFlow

Job description

The postdoctoral researcher position at the Laboratoire d'Écologie Alpine (CNRS, Université Grenoble Alpes and Université Savoie Mont Blanc) invites applicants to develop representation learning methods linking soil community composition to environmental conditions using six markers and environmental data.

You will work within the BIOM team on multimodal data from ORCHAMP observatory and advance reproducible analyses.