Precision Phenotyping Postdoctoral Scientist

Join Vylor—Powering the Future of Agriculture​

At Vylor, we’re advancing agriculture through breakthrough science—combining elite germplasm, cutting-edge biotech, and next-generation expertise in gene editing and molecular breeding. Our portfolio includes trusted industry brands like Pioneer®, Brevant®, and Hoegemeyer®, delivering performance farmers rely on.​

Join us to help scale innovation globally and shape what’s next in crop science.

The Precision Phenotyping Team within the Seed Product Development Group is seeking a highly motivated post-doctoral scientist to help shape the future of AI-enabled plant breeding through multimodal phenomics and predictive modeling.

This position will focus on developing next-generation approaches for predicting corn yield, agronomic performance, and breeding outcomes using large-scale precision phenotyping datasets collected from drones, ground-based robotics, LiDAR, RGB imaging, hyperspectral sensing, thermal imagery, environmental measurements, and genomic information.

The successful candidate will work at the intersection of plant breeding, artificial intelligence, computer vision, and data science to develop novel phenomic features, foundation models, and multimodal machine learning approaches that transform raw sensor data into actionable breeding insights. This role offers the opportunity to advance cutting-edge research while delivering practical solutions that directly impact breeding decisions and product advancement.

Our team develops and deploys precision phenotyping technologies across global breeding programs and is actively advancing the next generation of AI-driven phenomics. The incumbent will help design and execute scientific research programs, develop scalable analytical pipelines, collaborate across breeding and technology teams, and translate emerging AI capabilities into production-ready breeding solutions.

An ability to work independently, think creatively, and collaborate across multidisciplinary teams is critical. Experience in machine learning, computer vision, deep learning, statistics, phenomics, or related computational disciplines is highly desirable.

What You’ll Do:

• Collaborate on a scientific research program focused on multimodal AI-driven prediction of corn yield, agronomic performance, and breeding outcomes using large-scale phenotyping datasets.
• Develop and evaluate novel phenomic features from multimodal sensor data including RGB, LiDAR, hyperspectral, multispectral, thermal, environmental, and genomic datasets.
• Design, train, and validate machine learning and deep learning models including multimodal architectures, transformer-based models, representation learning approaches, and foundation models for agricultural prediction tasks.
• Discover and characterize latent-space phenotypes derived from multimodal sensing platforms and evaluate their utility for breeding selection, environmental characterization, and genotype-by-environment analyses.
• Build scalable data processing, feature engineering, and model training pipelines capable of supporting large-volume phenotyping datasets collected across years, locations, and environments.
• Collaborate closely with breeders, quantitative geneticists, data scientists, software engineers, and sensor technology teams to translate research advances into breeding applications.
• Quantify model performance, biological interpretability, uncertainty, and failure modes while communicating results to both technical and business stakeholders.
• Publish scientific findings, contribute to intellectual property, and help maintain Vylor's leadership position in AI-enabled phenomics and predictive breeding.

What Skills You Need:

• Experience developing machine learning, deep learning, or AI models for prediction, classification, or representation learning applications.
• Experience with state-of-the-art deep learning frameworks such as PyTorch, TensorFlow, JAX, Lightning, or Hugging Face ecosystems.
• Experience developing yield prediction, genomic prediction, phenotype prediction, crop modeling, or genotype × environment prediction frameworks.
• Experience extracting quantitative plant traits from RGB, LiDAR, hyperspectral, multispectral, thermal, and robotic sensing platforms.
• Experience with statistical genetics, plant breeding, quantitative genetics, crop science, phenomics, or agricultural AI applications.

What Makes You Stand Out:

• Experience with multimodal data integration involving imagery, sensor, environmental, genomic, or time-series datasets.
• Experience with computer vision, self-supervised learning, contrastive learning, transformer architectures, graph neural networks, or foundation models.
• Experience with LiDAR point cloud processing, 3D reconstruction, sensor fusion, or digital twin frameworks.
• Experience managing large-scale cloud computing or MLOps environments including AWS, Azure, Kubernetes, Docker, MLFlow, or related technologies.
• Publications in high-impact journals, conference proceedings, patents, open-source software contributions, or demonstrated technical innovation.

When applying for this position, please provide a current curriculum vitae. Please be prepared also to submit bibliography and poof of doctoral degree (e.g. copy of diploma, final transcripts, or letter from your university's registrar office indicating you will be eligible to graduate) and three letters of recommendation to the hiring team prior to an interview.

Please note: there is no relocation or visa sponsorship provided for this role.

Join us in building the next generation of AI-powered phenomics, where multimodal sensing, foundation models, and predictive breeding converge to transform how crop performance is measured, predicted, and improved. Start by applying to this opportunity today!

Are you a good match? Apply today! We seek applicants from all backgrounds to ensure we get the best, most creative talent on our team.

Vylor is an equal opportunity employer. We are committed to embracing our differences to enrich lives, advance innovation, and boost company performance. Qualified applicants will be considered without regard to race, color, religion, creed, sex, sexual orientation, gender identity, marital status, national origin, age, military or veteran status, pregnancy related conditions (including pregnancy, childbirth, or related medical conditions), disability or any other protected status in accordance with federal, state, or local laws.