The Swiss Data Science Center (SDSC) is a national research infrastructure in data science and artificial intelligence (AI) of the ETH domain, with EPFL and ETH Zurich as founding partners. Its mission is to support academic labs, hospitals, industry and public sector stakeholders, including cantonal and federal administrations, through their entire data science journey, from the collection and management of data to machine learning, AI, and industrialization.

The Swiss Data Science Center (SDSC) and the ETH Zurich’s Crop Science Group are seeking a Postdoctoral Researcher for the PhenoMix project, a Swiss National Science Foundation (SNSF) funded initiative.

This role sits at the intersection of machine learning, computer vision, agricultural sciences, and plant phenotyping. The position focuses on Automated Trait Estimation using Machine Learning, developing novel data science methods for crop mixture phenotyping.

Project background

The PhenoMix project addresses the critical challenge of automated phenotyping for crop mixtures -- a promising agricultural practice with significant potential for sustainable food production. The project leverages the Field Imaging Platform (FIP), a state-of-the-art high-throughput phenotyping facility, along with field experiments to generate unprecedented multi-modal datasets of pure stands and crop mixtures.

The postdoctoral researcher will create novel data science tools and automate processing of image time series, plant trait information, and 3D reconstructions. The work will bridge advanced machine learning methods with practical agricultural applications, developing models that can transfer knowledge across different imaging platforms and environmental conditions.

Job description

The postdoc will develop and implement cutting-edge machine learning approaches for automated trait estimation, focusing on:

• Foundation Models for Phenotyping: Leveraging and adapting pre-trained foundation models for crop trait estimation in both pure stands and crop mixtures.
• Domain Transfer Methods: Developing plant-aware image-based domain transfer techniques.
• 3D Reconstruction and Rendering: Creating 3D point clouds from multi-view setups and rendering realistic 2D images.
• Human-in-the-Loop Approaches: Implementing active learning strategies that incorporate expert feedback at inference time.
• Field Evaluation: Conducting rigorous qualitative and quantitative evaluations of developed models on farm field experiments.
• Data Product Generation: Preparing comprehensive time series datasets of derived products.
• Software Development: Developing and maintaining codebases for the implemented methods.

Profile

Education:

• PhD in relevant field such as computer science, machine learning, data science, or domain science with demonstrated expertise in machine learning and computer vision.
• Demonstrated research excellence through publications in relevant venues.

Technical and Research Expertise:

• Strong background in machine learning and deep learning, particularly computer vision.
• Solid experience with modern deep learning frameworks (PyTorch preferred).
• Proven ability in scientific programming and prototyping in Python.
• Ability to formulate research questions and design experiments independently.
• Experience handling large and complex multi-modal datasets.

We offer

Professional Development:

• A stimulating, collaborative, diverse and cross-disciplinary research environment.
• Opportunity to work with state-of-the-art phenotyping infrastructure and datasets.
• Access to computational resources and latest machine learning tools.
• Possibility to publish research in top-ranked conferences and journals.
• Involvement in supervision of MSc and BSc students.

Curious? So are we.

We look forward to receiving your online application with the following documents:

• Letter of Motivation (max 2 pages) explaining your interest in the position and relevant experience.
• Curriculum Vitae including publication list.
• Electronic copies of relevant academic diplomas, transcripts and certificates.
• Contact details from 2 to 3 references.
• Links to code repositories or portfolios (if available).

Apply online now