Position Responsibilities

• Apply state-of-the-art data science methods to extract insights from trial, survey and external data sources to provide climate smart and tailored agronomic recommendations at scale.
• Lead specific activities to modularize “white label” data analysis framework applying (but not limited to) process-based and empirical models to conduct research on yield prediction, improved technology targeting and impact modelling.
• Work closely with climate information service experts and software engineers to integrate seasonal crop forecasts to optimize planting dates and dynamic agronomic advisories.
• Contribute to conceptualization and development of robust yet practical decision support tools (DST) for the deployment of climate services and agronomic advisories within partners’ existing extension platforms.
• Collaborate effectively with all iSPARK project partners, providing guidance and building capacity around crop modeling and its applications for generating agronomic gain.
• Contribute to building and nurturing key partnerships in Africa working closely with NARS, Agricultural Services, Digital Partners, Farmer Organizations, and other CGIAR centers.
• Contribute to the development and maintenance of APIs to ensure seamless integration with partners’ systems and adherence to industry standards and best practices.
• Collaborate with cross-functional teams to identify technical requirements, design robust architectures, and implement efficient deployment pipelines, facilitating the timely dissemination of climate-informed agronomic advisories to end-users in diverse agricultural contexts.
• Contribute to and lead reporting and scientific paper writing.
• Participate in grant proposal writing and project management to secure funding for research projects deemed necessary and relevant.

Requirements

Educational Qualifications

• The candidate should ideally have a PhD degree in data science, crop or climate modeling, bioinformatics, biostatistics, or agronomy/soil science with strong computational skills. However, highly qualified candidates without a PhD but an MSc degree and relevant work experience are strongly encouraged to apply.

Core Competencies

• At least two years of data analytics and decision support tools development experience in agricultural applications.
• Demonstrated proficiency in statistical modeling techniques.
• Strong problem-solving abilities and analytical skills, with demonstrated ability to analyze complex datasets, identify patterns, and derive actionable insights to inform decision-making.
• Expert knowledge in applying ML/DL algorithms (including random forest, gradient boosting, support vector machines, neural networks) and ensemble methods to solve agronomic problems and optimize decision support systems.
• Strong R and Python programming skills, with demonstrated experience in designing, developing, and deploying automated and generic data analysis pipelines using these programming languages.
• Strong demonstrated ability to implement best practices in documenting and sharing code, including use of version control systems (e.g., Git).