MedicalAIResearcher

ABOUT THE ROLE This role involves conducting rigorous, independent evaluations of medical imaging AI systems, bridging the gap between benchmark performance and clinical reliability. You'll work directly with medical imaging companies preparing regulatory submissions, owning customer engagements end-to-end—from defining evaluation questions to delivering evidence that informs go/no-go decisions. You'll combine practical ML skills with customer-facing judgment to understand model behavior, generalization, and uncertainty in real-world workflows. WHAT YOU'LL DO - Lead end-to-end customer engagements: run meetings, define evaluation questions, and scope investigations. - Design and execute investigations that characterize model behavior, generalization, failure modes, and remaining uncertainty. - Analyze medical imaging workflows (DICOM/PACS, radiology pipelines) and translate findings into actionable evaluation evidence. - Deliver clear, defensible reports and presentations for regulatory and internal audiences under tight timelines. - Collaborate with customers and cross-functional teams to inform go/no-go decisions and drive impact on product strategy. WHAT WE'RE LOOKING FOR - Strong CS fundamentals; degree in Computer Science, Engineering, Math, or related field (or equivalent practical experience). - Several years of experience in ML evaluation or medical imaging AI, with practical MLOps and model evaluation skills. Proficiency in Python and common ML frameworks, plus Docker and Kubernetes. - Hands-on expertise with medical imaging workflows and integration (DICOM/PACS, radiology pipelines) and integrating ML models into clinical systems; healthcare industry experience preferred. - Familiarity with regulatory considerations for medical AI (FDA submissions such as 510(k) or De Novo) is a plus.