Data engineer

• Build robust data ingestion pipelines for multi-modal datasets consisting of gigapixel images paired with genomic results and clinical metadata
• Together with the Software Engineer, design unit testing, logging, and controls to ensure a high-quality and complete data warehouse spanning structured and unstructured data
• Ensure data quality, consistency, and traceability by authoring the ML platform that enables training, evaluation, deployment, and monitoring of ML models
• Develop FDA- and IVDR-compliant frameworks for dataset access control, model versioning, and experiment tracking that align with regulatory strategy and jurisdictional requirements
• Innovate on existing image processing methods, in collaboration with our ML Engineers
• Develop containerized, production-grade services for model inference in an on-premises, cloud computing, or OEM-integrated context.

• 4+ years of experience:

• Building scalable pipelines for large-scale structured and unstructured data, using Infrastructure-as-Code (IaC) e.g. Terraform, Cloudformation, etc.
• Building solutions for distributed or high-performance data processing with reproducible, version-controlled infrastructure
• Experience with data modeling, distributed or high-performance data processing, experiment tracking, and MLOps in a production environment

• 2+ years experience developing data or ML systems, preferably in a regulated environment (e.g. medical devices, healthcare, financial services) with an understanding of requirements such as reproducibility, auditability, and data governance
• Fluent in python and familiar with at least one deep learning framework (e.g. PyTorch, TensorFlow)
• Effective communication (English) and interpersonal skills.
• Valid work permit in Switzerland or EU and availability to travel to Tunisia.

Strong plus:

• Exposure to ISO 27001 / ISO 13485 a plus
• Exposure to Software as a Medical Device (SaMD) or clinical integrations is a strong plus