Company Description As a global leader in crop protection solutions, we help farmers combat threats and ensure sufficient safe, nutritious, and affordable food for everyone – while minimizing the use of land and other agricultural resources.

Syngenta Crop Protection ensures crop safety from planting to harvest. From seed sowing to crop harvest, crops need protection from weeds, insects, and diseases, as well as from droughts and floods, heat and cold.

Job Description

Role Purpose

• Data Analyst for identifying product and business growth opportunities, making more objective decisions based on facts and data to increase sales volume.

Responsibilities

• Develops and supports statistical logic, machine learning, and rule-based analytics for products + digital services, including crop development, disease and pest risk, harvest timing, product recommendations, and other agronomic use cases.
• Independently structures analytical tasks, defines methodology, selects appropriate analytical approach, and translates business or agronomic hypotheses into measurable data logic.
• Integrates, processes, cleans, and validates data from various sources, including agronomic observations, weather data, field operations, remote sensing, product, marketing, and business datasets.
• Prepares datasets for products and services, experimental analysis, field validation, model development, and service quality monitoring.
• Identifies patterns, anomalies, thresholds, and key influencing factors using statistical analysis, machine learning, exploratory analysis, and domain-based interpretation.
• Develops and maintains analytical reports, dashboards, and visualizations to monitor Product+ service performance, validation results, implementation, and key business indicators.
• Calculates and interprets service quality metrics, including accuracy, response time, false positive rate, stability, effectiveness at regional and individual crop levels, and compares model and algorithm versions.
• Analyzes pilot and field trial results in collaboration with the Product+ Lead, technical experts, and field teams, providing rationale for decisions on testing, pilot launches, scaling, refinement, or termination.
• Provides data-driven recommendations and analytical justifications for Product+ roadmap development, service improvement, prioritization, and operational decision-making.
• Describes datasets, model logic, assumptions, limitations, metrics, versions, and recommendations to ensure transparency and reproducibility of analytical solutions.
• Communicates analytical results to technical and non-technical stakeholders, explaining model/service logic, limitations, and practical implications for Product+, marketing, sales, field teams, and developers.
• Provides targeted analytical support to Cropwise Pulse and other data and AI initiatives as needed, with a primary focus on Product+ digital services.

Qualifications

Knowledge, Experience, Education, and Abilities

Critical Knowledge:

• Higher education in Mathematics, Applied Mathematics, Statistics, or related quantitative disciplines.
• Deep knowledge of mathematical statistics, probability theory, and time series analysis.
• Proficiency in modern Python data analysis tools and frameworks:
  • pandas, numpy, scikit-learn, statsmodels, XGBoost, LightGBM, CatBoost
  • matplotlib, seaborn, plotly, SHAP
  • Jupyter, MLflow, Airflow (preferred)
• Understanding of SQL and relational databases.
• Practical experience with Git and GitHub/GitLab for version control, collaborative development, and reproducible analytical processes.
• Ability to read and interpret technical documentation in English.
• Practical experience with Artificial Intelligence and the ability to responsibly leverage Large Language Model-based assistants in analytical work, including code generation, debugging, exploratory analysis, feature engineering, model testing, documentation, and presentation of analytical results.

Critical Experience:

• Proven experience working with large and diverse datasets.
• Hands-on experience in developing and validating machine learning and statistical models.
• Ability to deliver comprehensive analytical solutions – from data collection to implementation.
• Experience presenting results to both technical and non-technical stakeholders.
• Understanding of agricultural business processes and associated risks.

Desirable Knowledge and Experience:

• Knowledge of causal inference methods and tools, especially DoWhy.
• Experience with geospatial data (GIS) and satellite imagery.
• Knowledge of MLOps practices and tools, such as DVC, Prefect, or Great Expectations.
• Experience in digital product development.
• Interest in or experience with agriculture and sustainable development. Critical thinking