Junior Data Scientist

The World Food Programme (WFP) is the leading humanitarian organization saving lives and changing lives, delivering food assistance in emergencies and working with communities to improve nutrition and build resilience.

As the international community has committed to end hunger, achieve food security and improved nutrition by 2030, one in nine people worldwide still do not have enough to eat. Food and food-related assistance lie at the heart of the struggle to break the cycle of hunger and poverty.

In 2020, WFP assisted 115.5 million people – the largest number since 2012 – in 84 countries.
For its efforts to combat hunger, for its contribution to bettering conditions for peace in conflict-affected areas and for acting as a driving force in efforts to prevent the use of hunger as a weapon of war and conflict, WFP was awarded the Nobel Peace Prize in 2020.

WFP’s efforts focus on emergency assistance, relief and rehabilitation, development aid and special operations. Two-thirds of our work is in conflict-affected countries where people are three times more likely to be undernourished than those living in countries without conflict.

In emergencies, WFP is often first on the scene, providing food assistance to the victims of war, civil conflict, drought, floods, earthquakes, hurricanes, crop failures and natural disasters. When the emergency subsides, WFP helps communities rebuild shattered lives and livelihoods. We
also
work to strengthen the resilience of people and communities affected by protracted crises by applying a development lens in our humanitarian response.

WFP development projects focus on nutrition, especially for mothers and children, addressing malnutrition from the earliest stages through programmes targeting the first 1,000 days from conception to a child’s second birthday, and later through school meals.

Assisting more than 115.5 million people in 120 + countries each year, the World Food Program (WFP) is the leading humanitarian organization saving lives and changing lives, delivering food assistance in emergencies, and working with communities to improve nutrition and build resilience. As the international community has committed to end hunger, achieve food security and improved nutrition by 2030, one in nine people worldwide still do not have enough to eat. Food and food-related assistance lie at the heart of the struggle to break the cycle of hunger and poverty.
WFP’s Regional office for the Middle East and Northern Africa (MENAEERO), based in Cairo, Egypt, provides strategic guidance, policy/technical support, and direction to WFP operations and activities in 16 countries: Algeria, Armenia, Egypt, Iran, Iraq, Jordan, Lebanon, Libya, Moldova, Morocco, State of Palestine, Syria, Tunisia, Turkey, Ukraine and Yemen. These country offices aim to assist roughly one-third of all of WFP’s beneficiaries (approx. 30 million) in some of the most critical humanitarian emergencies of our time. The regional office is also active in the ‘Changing Lives’ side of WFP’s mandate, helping national governments and local communities improve nutrition, livelihoods, school feeding, social protection, climate and disaster risk reduction, and other programs that build resilience and support development”.
This assignment is part of WFP Global AI initiatives. Thess initiatives aim to use AI to tackle the organization’s most pressing needs in coordination with HQ. This assignment is to support in the implementation of the AI use cases by designing, evaluating, benchmarking, and supervising the fine-tuning of various AI models.

Reporting to the Lead data scientist in the Data/AI team, the junior data scientist will provide support to provision the following tasks in support of the global AI initiatives:

1. Identify state of the art AI models that fits the use cases at hand.
2. Train/retrain AI models with relevant annotated datasets.
3. Model Evaluation and Optimization: Assess model performance, identify areas of improvement, and fine-tune hyperparameters to optimize the models. Use techniques like grid search or Bayesian optimization for parameter tuning. Exploratory Data Analysis (EDA): Perform EDA to gain insights into the data, identify patterns, correlations, and outliers. Use visualizations and statistical techniques to summarize and present the findings.
4. Feature Engineering: Create new features from existing data that can improve the performance of machine learning models. This includes feature extraction, transformation, and selection.
5. Natural Language Processing (NLP): Work on tasks related to text data, such as sentiment analysis, text classification, or named entity recognition. Utilize NLP libraries like NLTK, SpaCy, or Transformers.
6. Collaboration and Documentation: Collaborate with team members, document your work, and maintain a clear and organized record of your analysis, code, and results. Contribute to the organization's knowledge base or data science repository.
7. Other tasks as required.