As a Staff Machine Learning Engineer, you will play a pivotal role in developing innovative AI-powered medical technologies designed to improve cardiac diagnostics and patient outcomes. You will contribute to the development of machine learning models that analyze magnetocardiography (MCG) data to identify patients at high risk of coronary artery disease. Working at the intersection of machine learning, biomedical engineering, and clinical research, you will transform complex biosignal data into meaningful predictive insights. You will take ownership of feature engineering, clinical dataset quality, model development, and rigorous performance evaluation. Collaborating with multidisciplinary teams of scientists, clinicians, product specialists, and engineers, you will help bring advanced diagnostic technology from research into real-world clinical applications. This is an exciting opportunity to influence the development of next-generation software as a medical device (SaMD) within a highly innovative, research-driven environment.
Machine Learning Model Development: Design, develop, and train advanced machine learning models to identify high-risk coronary artery disease using magnetocardiography and other relevant biomedical signal data.
Biomedical Feature Engineering: Develop innovative predictive features from complex biosignal datasets, drawing on scientific literature, cardiac electrophysiology, and quantitative biomedical research to improve diagnostic accuracy.
Signal Processing and Analysis: Process, analyze, and interpret biomedical signals to identify meaningful patterns and biomarkers that can support clinical decision-making.
Clinical Data Management: Own the quality, preparation, and curation of clinical study datasets, transforming raw data exports from multiple clinical sites into clean, structured, analysis-ready datasets.
Data Quality Assurance: Identify inconsistencies, missing values, and data integrity issues, implementing appropriate validation and preprocessing procedures to ensure reliable model development and evaluation.
Model Evaluation and Validation: Conduct rigorous model testing, performance evaluation, and validation to assess predictive accuracy, reliability, and suitability for clinical applications.
Regulatory and Technical Documentation: Prepare verification and validation (V&V) documentation and technical evidence required to support regulatory submissions for diagnostic medical device software.
Clinical Study Collaboration: Work closely with clinical operations teams to support ongoing clinical studies, understand data collection requirements, and ensure machine learning workflows align with study objectives.
Cross-Functional Product Development: Collaborate with product, clinical, and engineering teams to define machine learning system requirements, translate clinical needs into technical solutions, and support product development.
Model Deployment: Contribute to deploying machine learning models into production environments using cloud-based infrastructure, ensuring solutions are reliable, scalable, and maintainable.
Scientific and Technical Innovation: Stay informed about emerging developments in biomedical signal processing, cardiac diagnostics, and machine learning to identify opportunities for improving diagnostic performance.
Research-Driven Development: Apply scientific research and evidence-based methodologies to develop new biomarkers, refine predictive algorithms, and advance the capabilities of emerging medical sensing technologies.
Technical Collaboration: Share expertise, communicate findings, and contribute to technical discussions within a multidisciplinary team focused on developing clinically meaningful innovations.