Expert Data Analyst — Health Informatics

Heritage Alliance Ltd is a health research and data science company based in Belgium, working with partners in Africa and internationally.

Who we are

We bring clinicians, statisticians and data scientists together to investigate health questions and translate findings into decisions that partners can use.

Health Data Sciences & Advanced Analytics: Statistical analysis, large-scale health-data processing, predictive modelling and federated learning across institutions.

Complex Clinical Research, including Clinical Trials and Implementation Science: Analytical support for observational studies, trials and evaluations of healthcare delivery, with attention to study design, bias and uncertainty.

Innovation & Digital Health Systems Development: Dashboards and analytical workflows that connect research findings with clinical, programme and policy needs.

A mission-driven environment: Use quantitative skills to address practical health questions in African and international collaborations.

Cutting-edge technologies: Work with modern statistical software, machine-learning frameworks and federated data infrastructure.

International exposure: Collaborate with health facilities, public-health institutions and research partners.

Growth and leadership opportunities: Develop from supervised analysis towards independent study delivery and technical mentorship.

We welcome applicants who can explain why an analysis is appropriate, demonstrate how it was implemented and communicate the scope and limitations of its results. Strong academic projects can provide evidence for junior appointments.

You will work with clinical investigators, data engineers and programme teams. Junior colleagues will deliver defined tasks with technical supervision; mid-career colleagues will take responsibility for analytical workstreams and review others’ work.

• Plan defensible analyses: Translate health questions into outcomes, cohort definitions and documented analysis plans; distinguish descriptive, predictive and causal objectives.
• Prepare complex health datasets: Clean and analyse longitudinal clinical records, registries, laboratory, survey and programme data; investigate missingness, inconsistent units, duplicates and selection bias.
• Apply sound biostatistics: Use appropriate regression, survival, longitudinal or multilevel methods; examine assumptions, quantify uncertainty and undertake sensitivity analyses.
• Work at scale: Write efficient SQL and R or Python workflows for datasets that exceed convenient desktop processing; use distributed processing when justified by data volume and infrastructure.
• Develop and validate machine-learning models: Build reproducible training pipelines; prevent patient-level, temporal and site leakage; assess discrimination, calibration, subgroup performance and external validity.
• Implement federated learning: Develop and evaluate models across participating data owners without centralising patient-level records; address differences between sites, class imbalance, local validation and aggregation strategies.
• Assess privacy and deployment constraints: Work with engineering and governance colleagues on controlled execution and disclosure review; understand that keeping raw data local does not by itself eliminate privacy risks.
• Build useful visualisations: Create dashboards and reports with clear denominators, definitions, refresh dates and uncertainty, using suitable tools such as Power BI, Shiny, Dash or Superset.
• Make analysis reproducible: Maintain version-controlled code, reusable functions, environment specifications and documentation; contribute to technical reports, manuscripts and partner training.

Travel and on-site work: Partner meetings and occasional training or implementation visits, according to project needs.

Essential

• A degree in biostatistics, statistics, mathematics, data science, epidemiology, health informatics or a related discipline with substantial quantitative training. A relevant master’s degree is preferred.
• Strong foundations in probability, statistical inference, linear algebra and model evaluation; ability to explain analytical assumptions and limitations.
• Practical proficiency in SQL and in R or Python, with the ability to build reproducible workflows and work with large or complex datasets.
• Strong understanding of machine learning and federated learning, supported by applied work. Familiarity with a framework such as Flower, or equivalent distributed modelling experience.
• Ability to interpret health data critically and communicate findings to both technical and clinical audiences.
• Fluency in English, a good command of French, and effective collaboration across disciplines and locations.

Expectations by appointment level

• Junior appointment: Evidence from a dissertation, internship or substantial portfolio showing statistical analysis, reproducible code, a dashboard and a machine-learning prototype with a demonstrable federated-learning component. Independent production leadership is not expected.
• Mid-career appointment: Evidence of independently delivering health-data analyses, handling large datasets, validating models and coordinating analytical work with multiple stakeholders; practical delivery of a federated modelling workflow is expected.

Desirable

• Experience with the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), the Observational Health Data Sciences and Informatics (OHDSI) ecosystem, or federated execution platforms such as Vantage6.
• Experience with causal inference, epidemiological modelling, distributed computing, privacy-enhancing methods or health research in African settings.

Remuneration: Negotiable, reflecting experience, responsibilities, duty station and contract arrangements.

Career development: Structured development in biostatistics, reproducible analytics and federated learning, with supervision appropriate to the appointment level.

Working environment: Multidisciplinary collaboration, access to relevant technical resources and opportunities to contribute to international health research. Benefits and working arrangements will be specified in the employment offer.

Women are encouraged to apply.