Job Description:

The key functions and deliverables of this role will include:

1. AI Model Development and Optimization

• Design, develop, train and optimize machine learning and deep learning models to strengthen the health system with AI capabilities.
• Conduct data preprocessing, feature engineering, model training, validation, tuning and performance optimization.
• Develop explainable AI pipelines to support clinical trust and regulatory transparency.
• Apply best practices in version control, experiment tracking, and reproducible ML workflows.

2. Deployment, MLOps and post-deployment monitoring

• Deploy AI models into secure, scalable production environments.
• Establish and maintain model performance monitoring, data and concept drift detection, automated retaining pipelines, and incident and rollback mechanisms.
• Optimize model inference speed, system reliability, and compute cost efficiency.
• Maintain structured model versioning, release management, and retirement protocols.

3. System integration and interoperability

• Integrate AI solutions with national digital health platforms, including EMRs, HMIS, LMIS, and other MoH systems
• Implement standards-based interoperability using APIs, HL& FHIR, and MoH recommended architecture patterns
• Develop real-time and batch data pipelines that enable secure AI inference in live workflows

4. Data Management, Quality and Security

• Work with NHIC data teams to access, clean, label, and manage large structured and unstructured datasets.
• Enforce data quality validation, bias detection, and representativeness checks.
• Implement secure data handling, encryption, access controls, and audit logging in compliance with national data governance and privacy laws.
• Maintain full dataset documentation and lineage tracking.

5. Model Evaluation, Testing, Clinical Validation and Regulatory support

• Conduct rigorous testing of AI models to ensure accuracy, fairness, and clinical relevance.
• Support clinical pilots, facility-level validation, and workflow integration testing.
• Prepare technical documentation for ethics committees, regulatory reviews, and audit processes.
• Perform error analysis and continuous refinement based on real-world clinical feedback.

6. Documentation, Reporting, and Knowledge Sharing

• Produce clear documentation for model architecture, training processes, deployment pipelines and integration workflows
• Provide inputs to technical reports, donor updates, concept notes and system design briefs.
• Support the development of user guides, SOPs, and training materials for health workers and system administrators.

7. Collaboration and Technical advisory

• Work closely with the other team members and departments within the health sector to improve and scale AI infrastructure
• Engage in weekly AI review sprints, technical design sessions and AI TWGs.
• Provide AI engineering support to Grant proposals, research collaborations, and public-private partnerships.

8. Continuous Learning and Innovation

• Stay updated on advancements in AI and AI technology
• Explore emerging tools and frameworks for national-scale deployments of AI solutions.
• Proactively propose new high-impact use cases for the health sector.

Required Qualifications

Qualifications and Requirements

Education

• Master’s degree (or higher) in AI, Computer Engineering, Data Science, Biomedical Engineering, Health Informatics or a closely related field.
• 4 – 5 years’ experience in Applied Machine learning, AI system development and production-grade deployments

Technical Expertise

• Strong experience in APIs, data pipelines, training workflows, deployment, maintenance and ML frameworks and systems integration.
• Hands-on experience across the full LLM stack, including model pretraining, fine-tuning, evaluation, and serving.
• Demonstrated ability to design and implement scalable model evaluation frameworks, including model-based assessment techniques.
• Advanced knowledge of reinforcement learning, including algorithm design, environment interaction, and performance evaluation.
• Strong engineering capabilities for rapid iteration on data pipelines, training workflows, deployment, and maintenance.
• Proven experience deploying and sustaining healthcare IT systems or medical AI agents in real-world environments.

• Design, develop, train and optimize machine learning and deep learning models to strengthen the health system with AI capabilities.
• Conduct data preprocessing, feature engineering, model training, validation, tuning and performance optimization.
• Develop explainable AI pipelines to support clinical trust and regulatory transparency.
• Apply best practices in version control, experiment tracking, and reproducible ML workflows.
• Deploy AI models into secure, scalable production environments.
• Establish and maintain model performance monitoring, data and concept drift detection, automated retaining pipelines, and incident and rollback mechanisms.
• Optimize model inference speed, system reliability, and compute cost efficiency.
• Maintain structured model versioning, release management, and retirement protocols.
• Integrate AI solutions with national digital health platforms, including EMRs, HMIS, LMIS, and other MoH systems
• Implement standards-based interoperability using APIs, HL& FHIR, and MoH recommended architecture patterns
• Develop real-time and batch data pipelines that enable secure AI inference in live workflows
• Work with NHIC data teams to access, clean, label, and manage large structured and unstructured datasets.
• Enforce data quality validation, bias detection, and representativeness checks.
• Implement secure data handling, encryption, access controls, and audit logging in compliance with national data governance and privacy laws.
• Maintain full dataset documentation and lineage tracking.
• Conduct rigorous testing of AI models to ensure accuracy, fairness, and clinical relevance.
• Support clinical pilots, facility-level validation, and workflow integration testing.
• Prepare technical documentation for ethics committees, regulatory reviews, and audit processes.
• Perform error analysis and continuous refinement based on real-world clinical feedback.
• Produce clear documentation for model architecture, training processes, deployment pipelines and integration workflows
• Provide inputs to technical reports, donor updates, concept notes and system design briefs.
• Support the development of user guides, SOPs, and training materials for health workers and system administrators.
• Work closely with the other team members and departments within the health sector to improve and scale AI infrastructure
• Engage in weekly AI review sprints, technical design sessions and AI TWGs.
• Provide AI engineering support to Grant proposals, research collaborations, and public-private partnerships.
• Stay updated on advancements in AI and AI technology
• Explore emerging tools and frameworks for national-scale deployments of AI solutions.
• Proactively propose new high-impact use cases for the health sector.

• Applied Machine learning
• AI system development
• Production-grade deployments
• APIs
• Data pipelines
• Training workflows
• Deployment
• Maintenance
• ML frameworks
• Systems integration
• LLM stack (model pretraining, fine-tuning, evaluation, serving)
• Scalable model evaluation frameworks
• Model-based assessment techniques
• Reinforcement learning (algorithm design, environment interaction, performance evaluation)
• Rapid iteration on data pipelines, training workflows, deployment, and maintenance
• Deploying and sustaining healthcare IT systems or medical AI agents in real-world environments

• Master’s degree (or higher) in AI, Computer Engineering, Data Science, Biomedical Engineering, Health Informatics or a closely related field.
• 4 – 5 years’ experience in Applied Machine learning, AI system development and production-grade deployments
• Strong experience in APIs, data pipelines, training workflows, deployment, maintenance and ML frameworks and systems integration.
• Hands-on experience across the full LLM stack, including model pretraining, fine-tuning, evaluation, and serving.
• Demonstrated ability to design and implement scalable model evaluation frameworks, including model-based assessment techniques.
• Advanced knowledge of reinforcement learning, including algorithm design, environment interaction, and performance evaluation.
• Strong engineering capabilities for rapid iteration on data pipelines, training workflows, deployment, and maintenance.
• Proven experience deploying and sustaining healthcare IT systems or medical AI agents in real-world environments.