Modelling Platform Science Lead

At Syngenta Crop Protection there has been significant focus and investment in predictive science and digital transformation, revolutionizing research and development for sustainable food production. We have recently developed PRIME, a cutting-edge predictive modelling platform, and we are seeking a talented individual to lead its success.

As the Modelling Platform Science Lead, you will provide strategic direction, guide technical and scientific governance, and bridge the gap between the R&D expert modelling community and R&D IT. Your role involves supporting diverse modelling communities across R&D, identifying new opportunities for model deployment at scale, and exploring new technologies for model building and validation. You will be accountable for the overall success of the platform, providing strategic direction and guiding technical and scientific governance aspects.

If you are passionate about science and innovation, with expertise in data science and predictive modelling, join us and become part of a dynamic network of data science practitioners contributing to the success of our organisation.

What are we looking for?

1. Background in predictive modelling in the physical or life sciences at a postgraduate level.
2. Prior wet-lab experience (e.g. biology, chemistry, toxicology, environmental science) is a plus.
3. Experience working in an academic or industrial R&D setting.
4. Strong Python skills and familiarity with standard data science tooling for data-driven modelling / machine learning.
5. Understanding of the model lifecycle and tools to manage it, as well as technical aspects such as deployment, containerization/virtualization, and handling metadata. Experience with DataIKU/DSS is a plus, but not essential.
6. Strong analytical thinking and problem-solving skills, adaptability to different business challenges and openness to new solutions and different ways of working.
7. Curiosity and ability to acquire domain knowledge in adjacent scientific areas to effectively work across internal teams and quickly get up to speed with different modelling approaches.
8. Understanding of mathematical/mechanistic modelling is a plus.