Texas A&M Agrilife Research is seeking to analyze large-scale agricultural datasets using AI/ML models to improve agronomic decisions.
Requirements
- Strong background in machine learning, predictive modeling, or applied AI
- Proficiency in Python and/or R; experience with libraries like scikit-learn, XGBoost, TensorFlow.
- Experience working with real-world datasets, especially those that are noisy, sparse, or high-dimensional.
- Experience with agricultural or environmental datasets (e.g., UAV, hyperspectral, soil health, crop yield).
- Familiarity with geospatial data and tools (e.g., GIS, QGIS, Google Earth Engine).
- Knowledge of explainable AI (e.g., SHAP, LIME), model interpretation, and/or uncertainty quantification.
- Familiarity with reproducible workflows and tools such as Git, Docker, or Jupyter Notebooks.
Responsibilities
- Design and implement AI/ML models to analyze large-scale agricultural datasets (e.g., field trials, satellite imagery, IoT sensor data).
- Develop pipelines for preprocessing, integration, and modeling of heterogeneous data (spatial, temporal, tabular)
- Conduct research in explainable AI and uncertainty quantification applied to agronomic decisions.
- Collaborate with agronomists, soil scientists, engineers, and other domain experts.
- Lead manuscript writing and present findings at conferences.
- Initiate and support grant writing and development of externally funded research proposals.
- Other duties as required.
Other
- Ph.D. in Soil and Crop Sciences, Statistics, Data Science, Computer Science, Agricultural Engineering, or a closely related field.
- Strong analytical, organizational, computer and communication skills.
- Ability to multi task and work cooperatively with others.
- Demonstrated record of peer-reviewed publications
- Interest in mentoring students and contributing to a collaborative research culture
