Jared Murundu

As a Student Intern in Machine Learning Algorithms at CIMMYT (International Maize and Wheat Improvement Center), I contributed to the development and implementation of machine learning models aimed at improving agricultural outcomes. My role involved preprocessing and cleaning agronomic, climatic, and remote sensing datasets for analysis, as well as training and validating models for crop yield prediction, disease detection, and soil fertility assessments. I worked closely with data scientists and agronomists to apply both supervised and unsupervised learning techniques, and I evaluated model performance using standard ML metrics. Additionally, I supported the integration of these models into research workflows, contributed to technical documentation and reporting, and participated in research seminars and capacity-building sessions organized by CIMMYT’s data science unit.

Data Collection and Analysis
Gather, clean, and preprocess large datasets from multiple sources.
Perform statistical and computational analyses using tools like Python, R, or MATLAB.
Generate insights and visualizations using data visualization tools (e.g., Power BI, Tableau).

Literature Review and Documentation
Conduct systematic literature reviews
Summarize technical papers and provide annotated bibliographies or research briefs.
Assist in writing research proposals, academic papers, and grant applications.

Experimentation and Simulation
Record outcomes and analyze system performance under various test conditions.

Technical Reporting and Presentation
Prepare research reports, white papers, posters, and presentation slides for academic and industry events.

Contribute to academic publishing efforts and conference submissions.

Administrative and Logistical Support
Coordinate meetings, manage project timelines, and support collaborative research efforts.

Maintain research databases, software licenses, and project documentation.

Stakeholder Engagement (Optional)
Interface with industry partners, NGOs, or government agencies in applied research projects.

Support training sessions or demonstrations related to research outputs (e.g., AI models, software tools).