Data Scientist Agriculture

Data Scientist - Agriculture

We have an exciting opportunity for Data Scientists to join our Global Data Analytics & Predictive Science Team in the Product Biology department. Within these roles you will work on Syngenta historical biological data to uncover patterns and deliver new data‑driven insights for active ingredient development across R&D functions. You will be asked to analyse and interpret the outcome of scientific experiments with your analytical skills as well as machine learning approaches.

Your work will bring forward our understanding of biological performance in crop protection and guide design optimisation and development of novel crop protection solutions.

We could consider candidates based at additional locations within Europe. You may be required to travel to international R&D locations and to work with collaborators globally.

Due to exceptionally high interest in this position we will only consider applications that include: (1) a CV, (2) a cover letter explaining your motivation and suitability for the role, and (3) a one‑page document in which you tell us how (with which tools and algorithms following which strategy) you would start exploring a 100MB CSV dataset of efficacy field trial results for a novel crop protection product including assessments for multiple crop types, trial sites and weather conditions.

Please upload your CV, your cover letter and the one‑page document in separate files named CV___, Cover

Letter___ and Answer___, replacing ___ with your family name.

• Driving historical data analysis of biological field trials by identifying patterns and analysing the impact of key factors, including product formulations, rates, mixtures, agricultural practices and environmental conditions, on product performance.
• Supporting domain experts in understanding product performance and identifying analytics opportunities to drive business value.
• Contributing to strategic business initiatives across Crop Protection R&D by interpreting physical chemistry, biokinetic, formulation, marketing and environmental data to support decision‑making and design laboratory, glasshouse and field trials.
• Guiding technical managers in designing field trials aimed at validating scientific hypotheses and model predictions.
• Working with R&D IT and software developers to improve data‑model integrations and to deploy applications tailored to shareholders’ needs.
• Monitoring and exploring new modelling approaches, analytical tools and methodologies.
• Engaging with high‑priority digital transformation projects to understand opportunities to accelerate the impact of data science for predictive field trialing.
• Working with colleagues and external collaborators to understand their complementary capabilities and to integrate them into projects and initiatives.

• Strong foundations in data science at postgraduate level with applications in natural sciences (e.g., biology, ecology, environmental sciences).
• Proven experience in the use of the main data‑science, analytics, modelling and visualization Python libraries, including machine‑learning and deep‑learning ones.
• Scientific domain knowledge in related fields such as environmental sciences or biology.
• Prior experience in developing machine‑learning models relevant to biological or crop protection outcomes.
• Hands‑on experience leveraging generative AI (genAI) approaches for data exploration, model development or research acceleration is a plus.
• Knowledge of data analysis and extracting data insights and new understanding while communicating scientific and data concepts to specialist and non‑specialist audiences.
• Adaptability to different business challenges and data types/sources and to learn and utili‑ze a range of different analytical tools and methodologies.
• Ability to visualise and story‑tell with data to communicate results to shareholders with different levels of technical proficiency.
• Analytical problem‑solving skills with innovative thinking while effectively collaborating across diverse teams and managing multiple priorities in a multicultural scientific environment.

We could…