Skip to Content

Senior Data Scientist

Customer: INAMI-RIZIV Avenue Galilée 5/011210 Bruxelles (Saint-Josse-ten-Noode)
Dates: 2026-09-07 2026-12-31
Arrangements: Full time, 40-hour week; hybrid working; teleworking possible 3 days/week and within Belgium; minimum 2 days/week in the Brussels office; flexible working hours from 07:30 to 20:00 with fixed slots 09:00-12:00 and 13:00-16:00.
Apply before: 2026-08-21

Description

The Data Office is the cornerstone of data and AI activities within NIHDI (INAMI-RIZIV). You will join a multidisciplinary team of data scientists, data engineers, architects, analysts, project managers and healthcare experts. The team is developing the next generation of anomaly-detection solutions for large volumes of Belgian healthcare data. These solutions identify unusual billing patterns, prioritise high-risk cases and support medical and administrative controls with explainable, data-driven insights.

As Senior Data Scientist, you will lead the design, development and industrialisation of machine-learning solutions in Azure Databricks. You will develop anomaly-detection, risk-scoring and classification models using supervised and unsupervised techniques. You will define evaluation approaches covering accuracy, explainability and operational value. You will also collaborate on data and ML pipelines, feature engineering and integration while applying security, privacy, governance and responsible-AI requirements.

The role combines hands-on advanced analytics with technical leadership and cross-functional collaboration. You will work closely with healthcare experts, data engineers, business analysts and policy stakeholders to translate business needs into scalable analytical solutions. The environment uses Python, SQL, PySpark, MLflow, Delta Lake, Unity Catalog, Databricks Workflows and multiple Azure services. The assignment is hybrid in Brussels, with flexible hours and teleworking possible three days per week within Belgium.

Top Reasons to Apply
Societal healthcare impact
Advanced AI challenges
Technical leadership role
Modern Azure stack
Multidisciplinary expert team
Responsibilities
Lead ML solution industrialisation
Collaborate healthcare business stakeholders
Develop anomaly detection models
Develop risk scoring models
Develop classification models
Define model evaluation approaches
Collaborate data ML pipelines
Engineer model features
Must Have
Relevant advanced degree
Ten years experience
Strong Python experience
Strong SQL experience
Strong Databricks experience
Strong PySpark experience
Machine learning knowledge
Anomaly detection knowledge
Nice to Have
Relevant sector experience

Detailed Responsibilities and Skills

Additional Responsibilities

  • Integrate analytical solutions
  • Use Databricks Azure services
  • Apply security privacy governance
  • Apply responsible AI requirements
  • Provide technical team leadership
  • Define technical standards
  • Coach team members

General skills

  • Master's or Ph.D. in Data Science, Computer Science, AI, Statistics, Mathematics, Engineering, or equivalent experience.
  • Minimum 10 years of experience in data science, machine learning, or advanced analytics.
  • Experience working in an agile environment.
  • Strong analytical and technical skills.
  • Pragmatic, autonomous, and delivery-focused.
  • Strong ownership and problem-solving mindset.
  • Able to translate business needs into scalable analytical solutions.
  • Clear communicator with strong ownership and leadership capabilities.
  • Strong focus on explainability, quality, and maintainability.
  • Team player, flexible, and eager to learn.
  • Mother tongue Dutch or French, with passive knowledge of the second national language.
  • Professional working proficiency in English.
  • Agreement to work in the Brussels office at least twice per week.
  • Agreement to telework only within Belgian borders.
  • Healthcare, insurance, fraud detection, or public-sector experience is a strong asset.

Technical skills

  • Strong experience with Python and SQL.
  • Strong experience with Azure Databricks and PySpark.
  • Strong knowledge of machine-learning techniques, including anomaly detection, classification, and clustering.
  • Experience with explainable AI, risk scoring, and large-scale data processing.
  • Experience with automated testing, CI/CD, and MLOps practices.
  • Ability to develop supervised and unsupervised machine-learning models.
  • Ability to define model evaluation approaches covering accuracy, explainability, and operational value.
  • Ability to collaborate on data/ML pipelines, feature engineering, and solution integration.
  • Ability to apply security, privacy, governance, and responsible-AI requirements.

Tools

  • Python
  • SQL
  • Azure Databricks
  • PySpark
  • Delta Lake
  • Unity Catalog
  • MLflow
  • Databricks Workflows
  • Azure Data Factory
  • Azure DevOps
  • Azure Storage
  • Git