The Research Associate will support AfriClimate AI’s applied research portfolio by contributing to the development, fine-tuning, and validation of AI-driven climate and weather modelling tools. Working closely with the research team, the successful candidate will play a hands-on role in data preparation, model development and evaluation, ensuring that research outputs are robust, open and relevant for African contexts.
Research & Development
- Assist in designing, implementing, and testing AI-based climate and weather forecasting methodologies.
 - Preprocess and manage large geospatial datasets (e.g., observational data, satellite products, reanalysis datasets).
 - Support the development of benchmarking frameworks for model evaluation, including skill scores, bias correction and uncertainty quantification.
 - Contribute to the setup and maintenance of MLOps pipelines for training, deployment and monitoring of AI models.
 - Collaborate with team members on documentation, and reproducibility of workflows.
 
Collaboration & Knowledge Sharing
- Work with meteorological agencies, universities and international partners on joint research tasks.
 - Contribute to open-source datasets, code repositories and technical documentation.
 - Support the preparation of research outputs, including peer-reviewed articles, technical reports, and policy briefs.
 - Present results in internal and external meetings (workshops and conferences).
 
Requirements
Essential Qualifications & Experience
- Master’s degree in Climate Science, Meteorology, Machine Learning or a related field.
 - Proficiency in Python.
 - Experience working with geospatial and gridded datasets (e.g., ERA5, CHIRPS, CMIP, satellite-based products).
 - Knowledge of machine learning methods applied to climate or weather problems.
 - Familiarity with standard model evaluation metrics and statistical analysis.
 - Ability to work independently as well as collaboratively in distributed teams.
 - Ability to communication technical work clearly.
 
Desirable Skills & Experience
- Previous research experience on African climate datasets and/or data-sparse contexts.
 - Hands-on experience with deep learning frameworks (e.g., PyTorch, TensorFlow).
 - Exposure to MLOps tools (e.g., MLflow, Docker, Kubernetes, Airflow).
 - Familiarity with cloud computing (AWS, GCP, Azure) or HPC workflows.
 - Knowledge of numerical weather prediction (NWP) systems, downscaling, or data assimilation.
 - Experience contributing to open-source projects or collaborative codebases.
 
Benefits
AfriClimate AI is a grassroots research organisation advancing climate resilience in Africa through open, community-driven AI research. We focus on developing region-specific datasets, tools, and methodologies to bridge the gap between global models and local needs, supporting equitable and actionable climate solutions across the continent.
- Mission-driven impact: Contribute to climate resilience and equity across Africa through open, locally grounded research.
 - Flexible, remote-first work: Collaborate with an international network while working from anywhere in Africa.
 - Open science ethos: Work in a fully open-source, community-driven environment that values transparency, reproducibility, and shared ownership.
 - Professional growth: Access mentorship, attend leading conferences, and shape the future of climate AI research in the Global South.
 - Collaborative culture: Join a multidisciplinary, values-aligned team working at the intersection of science, technology, and social impact.
 - Travel opportunities: Participate in key events, workshops, and field collaborations across Africa and beyond.
 - Competitive compensation: Receive a salary package that reflects your expertise, with flexibility for different levels of experience and location.
 
Top Skills
What We Do
                                    AfriClimate AI is a grassroots community dedicated to harnessing the power of Artificial Intelligence for a sustainable, prosperous and climate-resilient Africa.
                                
                            





