Postdoc in AI Foundation Models for Crop Microbiomes in Utrecht University – Netherlands

Summary

Utrecht University is offering a Postdoc position in AI Foundation Models for Crop Microbiomes, as part of the 5-year EIC Pathfinder project NOAH. The project aims to develop ARCA, an AI foundation model for crop microbiomes, to make context-dependent interactions learnable and predictable for climate-resilient and nutritious crops. The successful candidate will take a leading technical role in developing ARCA, working at the intersection of deep learning, bioinformatics, and microbial ecology. Responsibilities include designing, implementing, and benchmarking foundation-model architectures, developing representations, defining learning objectives, training and evaluating ARCA on large datasets, and applying interpretable AI approaches. The position is full-time, starting in January 2027, initially for one year with a potential extension of three years. The gross monthly salary ranges from €3,706 to €5,760. The application deadline is October 16, 2026.

Key Facts

Department	AI Technology for Life and Plant-Microbe Interactions groups, Faculty of Science
Position Type	Postdoctoral Researcher
Discipline	Agricultural sciences, Biological sciences, Computer science
Research Area	AI Foundation Models for Crop Microbiomes, AI-guided Root microbiome engineering, Deep learning, Bioinformatics, Microbial Ecology, Microbiome and Genome Data, Foundation Model, Transformer Masked-Autoencoder, Representation Learning, Self-supervised Learning, Generative AI, Diffusion Autoencoder, Interpretable Explainable AI, Microbial Taxa Functions
Degree Required	PhD or PhD close to completion
Experience	Recognised Researcher (R2)
Salary	Gross monthly salary between €3,706 and €5,760, salary scale 10 under Collective Labour Agreement Dutch Universities (CAO NU), based on a 38-hour working week. Includes 8% holiday pay and 8.3% year-end bonus.
Funding	EIC Pathfinder project NOAH
Contract Duration	Temporary, initially 1 year, extended with 3 years after positive evaluation. The project is a 5-year EIC Pathfinder project NOAH.
Deadline	2026-10-16
Employer Address	Padualaan 8, 3584CH Utrecht, Netherlands

About the Project

The NOAH project (AI-guided Root microbiome engineering for ClimAte-resilient and nutritious crops) aims to develop ARCA, an AI foundation model for crop microbiomes. This model will be trained on large-scale public and newly generated datasets to understand and predict how plant-associated microbiomes influence crop growth, nutrition, and resilience, considering context-dependent interactions with crop, soil, environment, and microbial communities. The project involves designing, training, and implementing ARCA, exploring various model architectures, learning objectives, and representation strategies. The model's predictions will be experimentally tested in greenhouse and field settings, with feedback loops for iterative improvement.

Key Responsibilities

• Design, implement, and benchmark foundation-model architectures for microbiome data, including transformer-based and masked-autoencoder approaches.
• Develop representations that integrate microbial identity and abundance with genomic or functional information and contextual metadata.
• Define and evaluate self-supervised learning objectives and embedding strategies, benchmarking their added value against simpler machine-learning baselines.
• Train and evaluate ARCA on large-scale microbiome datasets, considering sparsity, batch effects, scalability, generalisation, and uncertainty.
• Fine-tune ARCA for tasks like microbial root competence and crop-relevant outcomes, iteratively improving the model using experimental Design-Build-Test-Learn data.
• Develop a generative ARCA component, exploring autoencoder- and/or diffusion-based approaches for generating ecologically plausible microbiome configurations.
• Apply interpretable and explainable AI approaches to identify microbial taxa, functions, and contextual features driving model predictions.
• Develop reproducible training and evaluation workflows and collaborate with project partners to make models and associated tools usable beyond immediate research.

Required Skills

• Expertise in deep learning, bioinformatics, and microbial ecology.
• Ability to work with large-scale microbiome and genome data.
• Proficiency in designing, training, and implementing AI foundation models.
• Experience with transformer-based and masked-autoencoder architectures.
• Knowledge of self-supervised learning objectives and embedding strategies.
• Familiarity with generative AI approaches, including autoencoder- and/or diffusion-based methods.
• Understanding and application of interpretable and explainable AI approaches.
• Ability to develop reproducible training and evaluation workflows.
• Strong collaboration skills for interdisciplinary research and external partners.

Who Should Apply

This position is suitable for a Postdoctoral Researcher with a PhD or nearing completion of a PhD, who has experience as a Recognised Researcher (R2). Candidates should have a strong background in deep learning, bioinformatics, and microbial ecology, with an interest in developing AI foundation models for complex biological ecosystems, specifically crop microbiomes.

Benefits

• Central role in developing ARCA core AI technology within the five-year EIC Pathfinder project NOAH.
• Position available from January 2027, initially for 1 year, extendable by 3 years after positive evaluation.
• Gross monthly salary between €3,706 and €5,760 (salary scale 10 under CAO NU, based on a 38-hour week).
• 8% holiday pay and 8.3% year-end bonus.
• Pension scheme and partially paid parental leave.
• Flexible terms of employment based on CAO NU.
• Attractive additional benefits, including opportunities for personal and professional growth.
• Flexible leave arrangements and extra vacation days.
• Option to tailor employment package through the UU Terms Employment Options Model.
• Access to Utrecht University GPU/HPC infrastructure and large, curated microbiome and microbial genome datasets.
• Collaboration with NOAH partners at Aarhus University, Niab, INRAE, and The Hyve, including experimental teams.

About the Employer

Utrecht University is the organisation offering this Postdoc position, specifically within the AI Technology for Life and Plant-Microbe Interactions groups. The university provides GPU/HPC infrastructure and large, curated microbiome and microbial genome datasets for research. The position is part of an interdisciplinary research environment with close interaction with bioinformatics, microbial ecology, and experimental crop research.

Frequently Asked Questions

What is the main goal of the ARCA project?

The main goal of the ARCA project is to develop an AI foundation model for crop microbiomes to make context-dependent interactions learnable and predictable for climate-resilient and nutritious crops.

What is the duration of the contract?

The contract is temporary, initially for 1 year, with a potential extension of 3 years after a positive evaluation. The overall EIC Pathfinder project NOAH is a 5-year project.

What is the gross monthly salary range for this position?

The gross monthly salary ranges between €3,706 and €5,760, depending on qualifications and experience, based on salary scale 10 under the Collective Labour Agreement Dutch Universities (CAO NU).

When does the position start?

The position is available from January 2027.

What are the key benefits offered with this position?

Key benefits include a competitive gross monthly salary, 8% holiday pay, 8.3% year-end bonus, a pension scheme, partially paid parental leave, flexible employment terms, opportunities for personal and professional growth, flexible leave arrangements, and extra vacation days.

Will the AI model predictions be tested experimentally?

Yes, ARCA predictions will be tested experimentally in greenhouse and field settings, and the resulting microbiome and crop phenotype data will feed back into model development.