A large public-sector organisation is building production-grade machine learning services to improve decision support and automate operational processes. The team focuses on robust MLOps practices, integrating models into backend services and web frontends using C# .NET and Blazor, while model development and data work are performed in Python with structured experiment tracking and monitoring.
The mission
This role sits inside a multidisciplinary IT department of about 150 people that delivers regulated, bilingual digital services. The current initiative is to move several analytics and scoring pipelines from exploratory notebooks into reproducible, versioned ML-pipelines that run reliably both on cloud infrastructure and on-premise. Work follows SAFe principles and aims for traceable model lifecycle management compatible with European AI regulation.
Day to day you will own the end-to-end delivery of ML components: from data preparation and feature engineering to training, validation and production deployment. You will convert experiments into containerised services (Docker), implement CI/CD for model and service releases (Azure DevOps), and instrument models and pipelines for logging, metrics and drift detection using OpenTelemetry or Dynatrace. You will work in a team with data engineers, backend developers and architects and directly support business stakeholders by delivering reusable, well-documented ML services.
Your responsibilities
- Deliver production-ready ML services that are integrated into backend APIs or Blazor frontends, ensuring reproducibility and traceability
- Establish and maintain CI/CD pipelines, model registries and versioning practices so deployments are repeatable and auditable
- Build and validate models in Python using scikit-learn or PyTorch, with clear validation criteria and experiment tracking for comparisons
- Design and operate monitoring and alerting for model performance, latency, data drift and model drift using logging, metrics and observability tools
- Collaborate with data engineers to put reliable data transforms and feature stores in place, and ensure SQL-based production data processing is robust
- Document implementations, assumptions and operational runbooks, and coach colleagues on MLOps best practices
Your profile
Essential skills
- 3+ years in ML engineering or related software engineering experience delivering ML into production
- Strong experience with C# .NET and Blazor for integrating ML results into applications or backend services
- Proficiency in Python for data preparation, feature engineering, model training and validation (scikit-learn, PyTorch)
- Practical knowledge of containerisation with Docker and deployment patterns for services
- Experience with CI/CD and MLOps workflows, preferably using Azure DevOps, including experiment tracking and model registry concepts
- Solid SQL skills and experience processing data in production contexts
- Familiarity with monitoring and observability for ML (metrics, logging, drift detection, OpenTelemetry, Dynatrace)
- Ability to communicate technical choices to both technical and non-technical stakeholders and to work within multidisciplinary Agile teams
Languages
- Dutch C1 or French C1, plus comprehension of the other national language at B1 level
Education
- Bachelor’s degree in Computer Science, Data Science, Engineering or equivalent professional experience