Research Assistant — Machine Learning & Explainable AI (XAI)

Job Description:

The Research Assistant (RA) will work directly under the supervision of Dr. Osama Sohaib and contribute to the development and implementation of the CultureXAI framework for precision public health in the UAE. The RA will play a central role in key technical components of the project, including machine learning model development, explainable AI (XAI) implementation, open data analysis, and fairness and bias assessment across diverse population groups. The RA will be responsible for data preprocessing and integration from multiple health and demographic sources, designing and evaluating predictive models for non-communicable disease (NCD) risk, and applying XAI techniques (e.g., SHAP, LIME, counterfactual analysis) to generate interpretable and culturally-aware insights. The role also includes supporting the development of a prototype decision-support dashboard for policymakers and healthcare stakeholders. In addition, the RA will contribute to academic dissemination by assisting in the preparation of high-quality research publications (targeting Q1 journals), technical reports, and conference submissions, as well as supporting broader project dissemination activities. The position requires strong analytical, programming, and research capabilities, along with the ability to work effectively in an interdisciplinary research environment.

Minimum Qualifications:

- PhD in Business Analytics, Statistics, Data Science, Machine Learning, Computer Science, or a closely related quantitative discipline. - Strong foundation in machine learning, data analysis, and statistics - Proficiency in Python (e.g., Pandas, Scikit-learn) - Experience in developing dashboards or web-based applications (e.g., Flask, Streamlit, React)

Experience/Skills:

Experience: - 1â3 years (RA level) or 3+ years / PhD-level (Research Associate) - Experience working with real-world datasets and applied machine learning projects Technical Skill Set: - Machine learning: supervised/unsupervised learning, model evaluation, hyperparameter tuning - Explainable AI: model interpretability, feature importance, fairness and bias analysis - Programming: Python (required); familiarity with TensorFlow/PyTorch is a plus - Data handling: data cleaning, preprocessing, and multi-source data integration - Visualization: Matplotlib, Seaborn, Plotly, or dashboard tools (e.g., Streamlit, Flask) Research & Soft Skills: - Academic writing and contribution to publications - Literature review and analytical thinking - Ability to work independently and collaboratively in interdisciplinary teams

Preferred Qualifications:

- PhD in Machine Learning, AI, Data Science, or a related discipline - Prior experience in healthcare analytics, public health data, or applied AI research - Familiarity with explainable AI techniques (e.g., SHAP, LIME, counterfactual methods) - Experience with advanced ML models (e.g., XGBoost, Neural Networks)