Postdoctoral position in the development of an AI-based phenotyping system for high-throughput screening of aphid resistance in crops in controlled and field conditions Full-time

Postdoctoral Position In The Development Of An Ai-Based Phenotyping System For High-Throughput Screening Of Aphid Resistance In Crops In Controlled And Field Conditions

We are seeking applicants for an 18-months postdoctoral fellowship focusing on the development of an AI-based phenotyping system for high-throughput screening for aphid performances on pea plants. The position is available from the 1st of November 2026 or as soon as possible thereafter.

The aim of the project is to develop an AI-based phenotyping system for high-throughput screening of aphid resistance in plants both in controlled and field conditions. This tool will be used to screen for aphid resistance in a pea germplasm collection by characterizing aphid-traits related to their performances. In the long term, this will contribute to selection for aphid-resistant pea varieties contributing to sustainable organic agriculture in Denmark.

The appointed candidate will work in a highly experienced research environment, spanning basic biology to applied research for industry outcomes. The hosting team is a multidisciplinary group with expertise in applying various quantitative and statistical modelling approaches to biological systems (including crop genetics, host-pathogen interactions, pathogen population genetics, evolutionary biology…). The candidate will work in close collaboration with a specific group (DARSA) specialized in developing and applying remote-sensing tools and innovative open-source machine-learning methods.

Key responsibilities include:

• Develop effective collaborations with international scientists and industrial partners.
• Take responsibility for planning, executing, and interpreting research
• Characterize aphid traits related to the performances on partially resistant and susceptible plants.
• Develop an AI-assisted image-based phenotyping pipeline to automatically quantify aphid performances on the plants. This software will automatically count for aphids and accurately distinguish specific aphid-morphological traits (wings/no wings, estimated weight, different developmental stages and color differences, etc).
• Screen a pea collection for aphid resistance in controlled and field conditions.

We seek a highly motivated team member with a genuine interest in insect science, machine learning, plant breeding, as well as the ability to manage their own work.

Qualifications include:

1. PhD in computer science, computational biology, engineering, or related fields.
2. Experience developing deep-learning tools for image processing, automatic monitoring of agricultural pests, or high-throughput phenotyping
3. Solid background in mathematics and scientific programming (R, Python, etc.) along with effective logical reasoning skills
4. Experience with high-performance computing
5. Effective communication and writing skills in English
6. Experience writing scientific manuscripts for peer-reviewed journals