The Research Assistant (RA) will work under the supervision of Dr. Osama Sohaib and contribute to the development, implementation, and evaluation of the CultureXAI framework for precision public health in the UAE. The RA will play a key role in the technical and research activities of the project, including machine learning model development, Explainable Artificial Intelligence (XAI), open health data analytics, and fairness and bias assessment across diverse population groups. The RA will be responsible for collecting, preprocessing, integrating, and analysing publicly available health, demographic, and socioeconomic datasets; developing and evaluating predictive models for non-communicable disease (NCD) risk; and applying XAI techniques, including SHAP, LIME, and counterfactual analysis, to generate interpretable insights into population-specific risk factors. The RA will contribute to academic research and dissemination activities, including literature reviews, experimental design, technical documentation, research reports, conference papers, and high-quality journal publications, particularly targeting Q1-ranked journals. In addition, the role will also involve supporting the development and evaluation of a prototype decision-support dashboard to communicate analytical findings to public health authorities, policymakers, and other healthcare stakeholders. The successful candidate is expected to demonstrate strong analytical, programming, problem-solving, and academic research skills, with the ability to work independently and collaboratively within a multidisciplinary research environment.

Master's degree (MSc) in Computer Science, Artificial Intelligence, Data Science, Machine Learning, Information Systems, Statistics, or a closely related discipline.

PhD in a relevant discipline, particularly with research experience in Machine Learning, Explainable AI, Health Informatics, or Applied AI.

Experience: Demonstrated academic or practical experience in machine learning, data analysis, or AI-based research. Previous involvement in research projects, scientific publications, or applied machine learning development is desirable. Experience working with healthcare, public health, demographic, or socioeconomic datasets is an advantage. Required Technical Skills: Strong programming proficiency in Python. Experience with machine learning libraries such as Scikit-learn, XGBoost, Pandas, and NumPy. Knowledge of supervised learning, predictive modelling, model evaluation, and cross-validation. Practical understanding of Explainable AI, particularly SHAP and LIME. Experience in data preprocessing, feature engineering, statistical analysis, and visualisation. Ability to work with structured and aggregated datasets. Familiarity with Git, Jupyter Notebook, and reproducible research practices Preferred Skills: Experience implementing counterfactual explanations using DiCE or similar frameworks. Knowledge of algorithmic fairness, bias assessment, and subgroup performance evaluation. Familiarity with clustering methods, including Gaussian Mixture Models. Experience with causal inference or interpretable statistical modelling. Familiarity with public health analytics, epidemiological data, or health information systems.

Updated curriculum vitae (CV), including educational qualifications, technical skills, research experience, and publications (if any).

3K to 5K

11/12/2026