Postdoc in Self-Supervised Learning for Image-Based Phenotyping in Agriculture Wageningen University & Research in Netherlands

Wageningen University & Research is recruiting a Postdoc in Self-Supervised Learning for Image-Based Phenotyping within the chair Artificial Intelligence, led by Prof. Ioannis Athanasiadis, with co-supervision by Prof. Ricardo da Silva Torres and Prof. Athanasiadis.

The project sits at the intersection of computer science, agriculture, biology, statistics, and environmental science. The research focuses on self-supervised learning, foundation models, computer vision, and image-based phenotyping for crop improvement. You will work with large-scale, multi-temporal plant image datasets, including UAV and sensor data, to learn biologically meaningful representations of plant traits, stress responses, genetic variation, and genotype-environment interactions.

The postdoc is embedded in the PHENOM project and involves collaboration between Wageningen University & Research and Radicle Crops. A key crop in the project is quinoa, used as both a model and target crop for sustainable agriculture and breeding. The role is research-intensive and aims to support predictive breeding pipelines and practical breeding applications.

Applicants should have a completed PhD in AI, computer science, statistics, engineering, or a related field, plus strong applied machine learning experience. Experience in Python, PyTorch, Scikit-Learn, Git, and HPC environments is desirable. Background in plant breeding, self-supervised learning, or time-series analysis is a plus. English proficiency at C1 level is expected.

The position offers a two-year temporary contract (1+1) with a gross monthly salary of €3,546 to €5,538 for a full-time 38-hour week, with a possible 0.8 FTE arrangement. WUR also highlights benefits such as sabbatical leave, study leave, partially paid parental leave, a year-end bonus, pension, and an international working environment in Wageningen, Netherlands.

Applications must be submitted through the WUR website only. The deadline is 8 June 2026.