Biologicals Discovery Data Scientist

Corteva Agriscience is seeking an innovative, collaborative, and enthusiastic Data Scientist with a strong foundation in machine learning, deep learning, and life or physical sciences. The successful candidate will join a strong, globally distributed Data Science team applying advanced analytics and AI to accelerate biologicals discovery — spanning both microbial and natural products discovery — for crop health. This is a high-impact opportunity to shape how modern AI and predictive modeling are applied across these discovery pipelines, partnering closely with data scientists, data engineers, genomics and metabolomics scientists, chemists, and biologists to deliver differentiated solutions to agriculture. The preferred location for this position is our Corteva Global Headquarters in Indianapolis, Indiana, USA. What You’ll Do: Innovate at the interface of data science, chemistry, and biology to drive discovery of novel microbial and natural products solutions for crop health Develop predictive models that integrate genomic, metabolomic, and phenotypic data to characterize and prioritize promising candidates Build models that connect insights across discovery pipelines, helping identify opportunities that might otherwise be missed within a single pipeline Actively seek, evaluate, and implement modern AI/ML methods — including deep learning and modern architectures — to advance predictive modeling capabilities Partner with collaborators across domains to drive integrated discovery pipelines and candidate prioritization, selection, and advancement toward new microbial and natural products solutions What Skills You Need: Minimum MS with 5+ years of post-graduation work experience, or Ph.D., in quantitative fields (e.g., Data Science, Statistics, Mathematics, Computer Science) or in life or physical sciences (e.g., Biology, Chemistry) Strong understanding of biology, with the ability to critically evaluate model outputs to generate testable and business-relevant biological and biochemical hypotheses Demonstrated experience with modern machine learning and deep learning methods, including hands-on experience with a modern AI stack (e.g., PyTorch, transformer architectures, generative AI methods), and a solid understanding of the math and model behavior to make sound methodological judgment (e.g., appropriate training design, evaluation metrics, model calibration) Demonstrated ability to independently frame a research problem, define success criteria and evaluation approach, and clearly articulate findings — from early-stage ambiguity through to a well-structured, communicated result Strong foundation in Python or a similar programming language for data wrangling, analysis, and ML applications Excellent verbal and written communication skills with ability to work as part of a cross-functional project team Preferred Skills: Experience with multi-modal, integrative, or digital twin modeling approaches Experience integrating genomic, metabolomic, and/or phenotypic data for predictive modeling Experience with generative AI approaches applied to life sciences Experience or education in natural products chemistry/biochemistry or microbiology Experience deploying ML models to production, with MLOps practices such as version control, containerization, workflow orchestration, and reproducible, maintainable pipelines Practical knowledge and experience with cloud-computing systems and platforms Experience with agentic AI systems or tool-use/multi-agent architectures #LI-BB1 Benefits – How We’ll Support You: Numerous development opportunities offered to build your skills Be part of a company with a higher purpose and contribute to making the world a better place Health benefits for you and your family on your first day of employment Four weeks of paid time off and two weeks of well-being pay per year, plus paid holidays Excellent parental leave which includes a minimum of 16 weeks for mother and father Future planning with