Data Scientist

The Data Scientist will play a critical role in transforming large and complex datasets into actionable insights, predictive models, and AI-driven solutions that improve fundraising effectiveness and supporter engagement for WFP's Individual Fundraising programmes. The role involves collaboration with multiple teams to leverage advanced analytics, machine learning, and AI to optimize fundraising performance and donor value.

Responsibilities

• Provide data science, machine learning, and AI services in support of IF’s global data and analytics priorities, including deriving insights from large-scale datasets including transactional, web, app and experimental data.
• Collaborate with PSP stakeholders, data owners, product teams, and technical counterparts to translate business needs into analytical solutions, document methods and results, and support adoption of data-driven recommendations.
• Design, build, train, evaluate, and deploy machine learning and data science models that support segmentation, clustering, prediction, fundraising optimization and donor engagement.
• Apply advanced AI techniques, including natural language processing, large language models, retrieval-augmented generation, prompt engineering, and agentic workflows to automate analysis, improve decision support, and enhance knowledge discovery.
• Perform exploratory data analysis, feature engineering, model evaluation, hyperparameter tuning, and model optimization to ensure analytical outputs are accurate, explainable, scalable, and fit for purpose.
• Implement or assist tech and product teams to implement and operationalize data science models.
• Rigorously review model performance and refine or retire where appropriate, maintaining a repository of solutions.
• Contribute and collaborate with wider community of data scientists within WFP and sister agencies, keeping abreast and raising awareness to PSP colleagues of cutting-edge developments.
• Other tasks as required.

Requirements

• Six years of relevant experience plus a university degree in Computer Science, Artificial Intelligence, Data Science, Statistics, Engineering, or a related quantitative field.
• Demonstrated experience working with large-scale datasets and building machine learning or AI solutions is required.
• Working knowledge of cloud platforms and modern data science tooling is considered an advantage.
• Proficiency in programming languages such as Python or R is crucial for a data scientist.
• Solid understanding of statistics including hypothesis testing, regression analysis, probability distributions, and statistical modeling techniques.
• Expertise in traditional machine learning techniques including supervised and unsupervised learning, segmentation, clustering, prediction, classification, regression, feature engineering, model evaluation, and model selection.
• Strong experience with sentiment analysis, natural language processing, large language models, prompt engineering, retrieval-augmented generation, and agentic AI workflows, with ability to identify practical use cases and implement responsible AI solutions.
• Excellent oral and written skills; excellent drafting, formulation, reporting skills.
• Excellent interpersonal skills; culturally and socially sensitive; ability to work inclusively and collaboratively with a range of partners including grassroots community members, religious and youth organizations, and authorities at different levels.
• Ability to work and adapt professionally and effectively in a challenging environment; ability to work effectively in a multicultural team of international and national personnel.
• Self-motivated, ability to work on MVPs in an agile environment; ability to work with tight deadlines.
• Sound security awareness.
• Have affinity with or interest in leveraging AI in humanitarian domain volunteerism as an enabler for durable development, and the UN System.
• Proficiency (read/write/speak) in English.

Skills

• Data Science
• Machine Learning
• Artificial Intelligence
• Python Programming
• R Programming
• Statistical Modelling
• Hypothesis testing
• Regression Analysis
• Probability distributions
• Supervised learning
• Unsupervised learning
• Segmentation
• Clustering
• Prediction
• Classification
• Feature Engineering
• Model evaluation
• Model Selection
• Public Sentiment Analysis
• Natural Language Processing
• Large Language Models
• Prompt Engineering
• Retrieval-Augmented Generation
• Agentic AI Workflows
• Cloud Platforms
• Data Science Tooling
• Agile Methodologies
• Security Awareness
• Report Writing

Languages

English