Data Specialist – Agronomic Analytics and Modeling CIMMYT at World Agroforestry Centre (ICRAF)

Job Description

The World Agroforestry Centre, is an international institute headquartered in Nairobi, Kenya, and founded in . The Centre specializes in the sustainable management, protection and regulation of tropical rainforest and natural reserves.

Overview

This post will contribute to both bilateral projects requiring data analytics and ONECGIAR initiatives including Harnessing digital technologies (DX1) and AgriLAC Resiliente. This is a position within the MEAL team funded both by SAS project portfolio, as well as OneCGIAR initiatives and bilaterals in Asia (Bihar) and Africa (USAID).

Duties and responsibilities

Develop and implement best practices and protocols for data cleaning, analysis and modeling. Design and oversee the development of complex statistical models for agronomic data analysis. Implement machine learning and AI techniques to extract insights from large-scale agricultural datasets. Validate and refine models to ensure accuracy and reliability of results. Lead the development of methodologies for calculating key agricultural KPIs, including: Greenhouse Gas emissionsSoil health indicesSustainable practice adoption rates Ensure alignment of KPI calculations with international standards and best practices. Collaborate with breeding data teams to integrate data-driven insights into agronomic analyses. Implement data governance practices to ensure data integrity and security. Oversee the development and maintenance of data pipelines and storage systems. Prepare and present comprehensive reports on analytical findings to stakeholders Develop data visualizations and dashboards to communicate complex information effectively Collaborate with cross-functional teams to translate analytical insights into actionable recommendations.

Requirements

Ph.D. in Data Science, Statistics, Computer Science, or a related field. Minimum 5 years of experience in leading data science teams, preferably in an agricultural or environmental context. Strong background in statistical analysis, machine learning, and predictive modeling. Proficiency in programming languages such as R, Python, and SQL.