Post-Doctoral Associate - Pickering Lab

Post‑Doctoral Associate - Pickering Lab Department: CAES-Crop & Soil Sciences Position Summary Agentic AI is rapidly changing nearly every domain, from academia to industry. Agriculture is no different. This postdoctoral opportunity will look to research and build agentic scientific AI systems that can design, predict, and optimize agricultural outcomes—across crops, environments, and management regimes. We are seeking a Post‑Doctoral Associate to develop the next generation of Agentic AI for Agricultural Design and Prediction, spanning: Genomics agents that assemble AI‑native genomic prediction and selection models (e.g., DNA foundation‑models, GNN/sequence architectures for breeding decisions, pangenomic models). Crop Growth Model agents that create AI‑native crop growth models—including Bio‑Informed Neural Networks (BINNs) and hybrid dynamical systems that fuse mechanistic constraints with large‑scale data. Scientific agent workflows that can ingest literature + datasets, propose modeling choices, run experiments, quantify uncertainty, and iteratively improve models with human‑in‑the‑loop evaluation. This role sits at the intersection of applied mathematics, machine learning, genomics, crop science, and dynamical systems, and will be carried out in a highly interdisciplinary team environment. Potential Focus Areas Agentic Genomics for Prediction & Selection : Build agents that can automatically construct, evaluate, and adapt genomic/pangenomic/editing prediction pipelines (from raw genotypes/omics to breeding‑value predictions), including modern representation learning and uncertainty‑aware decision support. Agentic AI Crop Growth Models (AI‑CGMs) : Develop hybrid modeling agents that learn AI‑native CGMs (e.g., BINNs; constrained neural ODEs; spatiotemporal models) integrating genomics, phenomics, physiology, weather, soils, remote sensing, and management data. What Success Looks Like (12–24 months) A working agentic modeling stack demonstrated on at least one ''end‑to‑end'' crop use case (e.g., data > genomics predictions + AI‑CGM > intervention suggestions with uncertainty). Publications in top venues (ML for science, computational biology, agronomy/crop modeling) and public releases of code/benchmarks. Clear pathways to stakeholder deployment (breeders, agronomists, extension, or industry R&D). Relevant/Preferred Education, Experience, Licensure, Certification in Position Mathematical + computational depth, especially one or more of: Dynamical systems, scientific computing, numerical methods, optimization Probabilistic modeling / Bayesian methods / uncertainty quantification Representation learning for sequences/graphs; geometric deep learning Proficiency (or strong interest) in any of: Genomics, quantitative genetics, genomic prediction, GWAS, multi‑omics integration Crop growth modeling, ecophysiology, spatiotemporal modeling, remote sensing + agronomy Agentic AI / tool‑using LLM systems / workflow orchestration for science Knowledge, Skills, Abilities and/or Competencies Candidates should have strength in several of the following: Machine learning / deep learning; LLMs, GNNs, sequence models; hybrid modeling Linear algebra, optimization, probabilistic modeling, experimental design, active learning Scientific programming in Python (other languages a bonus); building maintainable, open‑source codebases and reproducible pipelines (containers, workflows, benchmarking) Ability to collaborate across disciplines and communicate clearly with both technical and domain audiences Physical Demands: Lifting 25 lbs, prolonged sitting at office desk. Is this a Position of Trust?: Yes Does this position have operation, access, or control of financial resources?: No Does this position require a P-Card?: No Is driving a requirement of this position?: No Does this position have direct interaction or care of children under the age of 18 or direct patient care?: No Does this position have Security Access (e.g., public safety, IT security, personnel records, patient records, or access to chemicals and medications): Yes Background Investigation Policy Offers of employment are contingent upon completion of a background investigation including a criminal background check demonstrating eligibility for employment with the University of Georgia; confirmation of the credentials and employment history reflected in your application materials (including reference checks) as they relate to the job‑based requirements of the position applied for; and, if applicable, a satisfactory credit check. You may also be subject to a pre‑employment drug test for positions with high‑risk responsibilities, if applicable. Please visit the UGA Background Check website. Contact Details Recruitment Contact: Ethan Pickering, View email address on click.appcast.io Equal Opportunity Employer Statement The University of Georgia is an Equal Opportunity employer. All qualified applicants will receive consideration for employment without regard to age, color, disability, genetic information, national origin, race, religion, sex, or veteran status or other protected status. Persons needing accommodations or assistance with the accessibility of materials related to this search are encouraged to contact Central HR (View email address on click.appcast.io). #J-18808-Ljbffr University of Georgia