Ideally looking for someone with a PhD (related to process based crop modeling (expert in Corn or Soy)) and some industry experience (Ag or seeding companies).

We are seeking a technically skilled individual to support the development of Genotype x Environment x Management models that provide agronomic insights for internal stakeholders and farmers. This individual will leverage large agricultural datasets from connected equipment (planters, sprayers, combines, etc.), weather data, soil maps, satellite and drone imagery, and other sources to build scalable agronomic decision-support models to improve productivity, profitability, and sustainability in corn, soybean, and cotton production systems. They will be responsible for ensuring that agronomic models are agronomically reasonable, properly calibrated and validated, transparent in their assumptions, and appropriate for the crops, geographies, and management systems in which they are deployed.

This position requires someone who has a deep understanding of agronomy in US corn, soy, or cotton production systems and experience building G x E x M models for predicting the outcomes of various management scenarios (planting date, variety selection, fertility management, crop care, etc.) across diverse geographies. This person will function as the agronomic modeling bridge between the technical development team and real-world corn, soybean, and cotton production systems.

Responsibilities
Develop modeling approaches for G x E x M interactions to predict the outcomes of various management scenarios (planting date, variety selection, fertility management, crop care, etc.) in corn, soybean and cotton production systems across diverse geographies.
Design and execute model calibration, validation, and sensitivity analyses to quantify model performance, uncertainty, and limitations across geographies, years, and management systems.
Understand interactions among genotype, weather, soil, management, and cropping history to clearly define modeling problems, input requirements, outputs, assumptions, and validation criteria.
Work with large, machine-generated agricultural datasets including planter, sprayer, harvest data.
Work with large geospatial datasets including soil maps, topography, multispectral imagery, remote sensing products, and environmental data layers.
Develop repeatable workflows for processing, summarizing, and visualizing outcomes of these models.
Develop agronomic logic, constraints, and validation frameworks that ensure AI-generated recommendations are agronomically sound, transparent, and scientifically defensible.
Collaborate with agronomists, data scientists, software developers, and product managers to build, scale, and communicate outcomes of these models.

Required Qualifications
Experience developing, calibrating, validating, and applying APSIM, DSSAT, or comparable process-based crop models for agricultural decision support.
Strong understanding of crop physiology, phenology, soil water dynamics, nutrient cycling, and their influence on crop response to management and environment.
Strong understanding of at least one major US row crop production system, with expertise in corn and soybean production preferred.
Advanced proficiency in R and/or Python for data analysis, simulation workflows, and model development.
Experience working with Databricks, SQL, cloud computing environments, APIs, for scalable analytical and simulation workflows.
Demonstrated experience with AI assisted development.
Experience working with large multi-environment, multi-year, or multi-management agricultural datasets and developing reproducible analytical workflows.
Ability to communicate model assumptions, results, limitations, and uncertainty to both technical and nontechnical audiences.
Experience translating scientific models or research outputs into practical decision-support tools, recommendations, or operational workflows for growers.
Master’s or Ph.D. in agronomy, crop science, soil science, biological systems engineering, agricultural engineering, quantitative genetics, or a closely related discipline.

Preferred Qualifications
Experience with Client Operations Center and precision agriculture technologies including planting, spraying, harvest, automation, sensing, and variable-rate management systems.
Familiarity with machine-generated datasets and common grower-facing agronomic data layers (field boundaries, management zones, digital elevation models).
Experience working in agricultural industry with agronomic model development.
Experience developing agronomic constraints or validation systems for AI-generated recommendations.
Experience integrating drone and satellite data into analytics pipelines.
Proficiency in SQL, R, Python, Tableau, Power BI, or similar tools.

Notes:
Person can be onsite, but will consider fully remote. If remote, would need to be available roughly 8-5 Central time. Would also need to be able to travel to Des Moines 1 or 2 times pers year.