About the Role

The Data Scientist will leverage AI/ML-driven predictive analytics to support the development and deployment of Proof-of-Concept (PoC) and Minimum Viable Products (MVPs) focused on NCD (Non-Communicable Diseases) patient retention, delivery forecasting, behavioral adherence, and AI-powered virtual assistants. The role involves building machine learning models for risk scoring, adherence prediction, and supply chain optimization while integrating insights into existing healthcare and logistics dashboards to improve patient outcomes and operational efficiency. Role can be based in Egypt, Rwanda, Kenya and/or South Africa.

Responsibilities

Predictive Analytics & AI Models

• Design and develop AI-driven risk scoring models to identify NCD patients at risk of disengagement.
• Build predictive models to forecast eligibility transitions for improved patient care pathways.
• Implement a Machine Learning-based adherence segmentation model to analyze patient behavior patterns.

Delivery Forecasting & Supply Chain Optimization

• Develop an AI-powered delivery forecasting model to predict medication delivery accuracy and potential delays.
• Integrate predictive insights into logistics and warehouse management systems to improve proactive planning.

AI-Powered Virtual Assistants

• Develop and deploy AI-powered chatbots and virtual assistants for medication reminders, real-time patient engagement, and adherence support.
• Enable self-service patient platforms for medication-related queries and preference management.

Data Engineering & Infrastructure

• Design and optimize Python-based ETL pipelines for data flow between AI models and healthcare dashboards.
• Work with MS Dynamics integrations to enhance AI-driven decision-making in clinical and operational processes.
• Ensure seamless API integrations for real-time data exchange between predictive models and user-facing applications.

Monitoring, Validation & Deployment

• Develop real-time monitoring mechanisms for risk stratification insights and adherence dashboards.
• Optimize CI/CD pipelines for AI/ML model deployment and automate API-based data updates.
• Conduct model validation, A/B testing, and performance tuning to refine PoC models before MVP scaling.

Collaboration & Knowledge Sharing

• Work closely with healthcare professionals, supply chain teams, and DevOps engineers to align AI models with operational needs.
• Provide executive-level data insights through Jupyter notebooks and visualization dashboards.
• Contribute to AI/ML best practices through code reviews, documentation, and team knowledge sharing.

Qualifications

Machine Learning & AI: Supervised and unsupervised learning, risk prediction models, forecasting algorithms.

Programming & Data Processing: Python, SQL, Pandas, Scikit-learn, TensorFlow/PyTorch.

Cloud & Infrastructure: AWS (RDS, Lambda, SageMaker), Google Cloud, or Azure AI services.

ETL & Data Engineering: Experience with building scalable data pipelines for ML models.

APIs & Integration: REST APIs, MS Dynamics API, healthcare data interoperability.

Visualization: Jupyter, Power BI, or similar platforms.

Experience

3+ years of experience in Data Science, AI/ML, or predictive analytics in healthcare, logistics, or enterprise AI applications.

Microsoft Data Analyst Associate certification or BSc in Computer Science, AI, or a related field.

Knowledge

Strong communication skills for engaging clinical teams, engineers, and business stakeholders.

Ability to translate complex AI insights into actionable business strategies.

Experience in healthcare analytics, supply chain optimization, or chatbot development is a plus.

• Design and develop AI-driven risk scoring models to identify NCD patients at risk of disengagement.
• Build predictive models to forecast eligibility transitions for improved patient care pathways.
• Implement a Machine Learning-based adherence segmentation model to analyze patient behavior patterns.
• Develop an AI-powered delivery forecasting model to predict medication delivery accuracy and potential delays.
• Integrate predictive insights into logistics and warehouse management systems to improve proactive planning.
• Develop and deploy AI-powered chatbots and virtual assistants for medication reminders, real-time patient engagement, and adherence support.
• Enable self-service patient platforms for medication-related queries and preference management.
• Design and optimize Python-based ETL pipelines for data flow between AI models and healthcare dashboards.
• Work with MS Dynamics integrations to enhance AI-driven decision-making in clinical and operational processes.
• Ensure seamless API integrations for real-time data exchange between predictive models and user-facing applications.
• Develop real-time monitoring mechanisms for risk stratification insights and adherence dashboards.
• Optimize CI/CD pipelines for AI/ML model deployment and automate API-based data updates.
• Conduct model validation, A/B testing, and performance tuning to refine PoC models before MVP scaling.
• Work closely with healthcare professionals, supply chain teams, and DevOps engineers to align AI models with operational needs.
• Provide executive-level data insights through Jupyter notebooks and visualization dashboards.
• Contribute to AI/ML best practices through code reviews, documentation, and team knowledge sharing.

• Machine Learning & AI: Supervised and unsupervised learning, risk prediction models, forecasting algorithms.
• Programming & Data Processing: Python, SQL, Pandas, Scikit-learn, TensorFlow/PyTorch.
• Cloud & Infrastructure: AWS (RDS, Lambda, SageMaker), Google Cloud, or Azure AI services.
• ETL & Data Engineering: Experience with building scalable data pipelines for ML models.
• APIs & Integration: REST APIs, MS Dynamics API, healthcare data interoperability.
• Visualization: Jupyter, Power BI, or similar platforms.
• Strong communication skills for engaging clinical teams, engineers, and business stakeholders.
• Ability to translate complex AI insights into actionable business strategies.

• Machine Learning & AI: Supervised and unsupervised learning, risk prediction models, forecasting algorithms.
• Programming & Data Processing: Python, SQL, Pandas, Scikit-learn, TensorFlow/PyTorch.
• Cloud & Infrastructure: AWS (RDS, Lambda, SageMaker), Google Cloud, or Azure AI services.
• ETL & Data Engineering: Experience with building scalable data pipelines for ML models.
• APIs & Integration: REST APIs, MS Dynamics API, healthcare data interoperability.
• Visualization: Jupyter, Power BI, or similar platforms.
• Microsoft Data Analyst Associate certification or BSc in Computer Science, AI, or a related field.