Sr Validation Engineer

In this Senior Validation Engineer role, you design and run manual and automated tests to ensure AI-enabled clinical workflows perform as intended and can be demonstrated with evidence. You’ll build and maintain a test automation framework, focusing on data integrity and patient safety within AI governance. You collaborate with data scientists, software engineers, and governance teams to deliver auditable validation under QMS and GCP-regulated clinical data science. This is a hands-on role with impact on quality, compliance, and reliability at scale.

• Design, execute and document manual and automated tests in Python or similar to produce reproducible evidence
• Evaluate system architecture, integrations, cybersecurity and data integrity; develop validation documentation from design specs to risk assessments
• Build and integrate a reusable test automation framework with CI/CD workflows; ensure test code is version-controlled and peer-reviewed
• Assess open-source packages for use, security, licensing, and defects; document actions and recommend alternatives
• Test workflows involving omics, imaging and digital-device data, ensuring input/output integrity, transformations, annotations, and audit trails
• Collaborate with AI specialists to evaluate models against context of use, datasets, metrics and acceptance criteria; separate software defects from model limitations
• Work under Novo QMS and GCP-regulated requirements to ensure evidence supports intended use
• Prepare technical documentation covering design specifications, risk assessments and validation plans

• Degree in computer science, data science, engineering, mathematics or related discipline, or equivalent experience
• Manual and automated testing experience (Python or similar)
• Experience with Git, code review, CI/CD, reusable test components and reproducible data analysis
• Strong IT understanding of software architecture, APIs, integrations, execution environments and data-processing workflows; experience with Microsoft Azure and Databricks
• Understanding of risk-based validation and data integrity; ability to judge if test evidence supports intended use
• Proactive, investigative mindset with clear written documentation of technical findings
• Motivation to develop expertise in GCP-regulated clinical data science, AI evaluation and new data modalities

• Collaborative mindset
• Proactive and investigative approach
• Clear written communication
• Python testing and test automation
• Manual testing and test design
• CI/CD integration and test-data generation