Data Scientist

Overview

Many structural heart patients suffer from heart failure with limited options. Our Implantable Heart Failure Management (IHFM) team, part of the AI, Product and Platforms organization, is at the forefront of addressing these unmet patient needs through pioneering technology that enables early, targeted therapeutic intervention.

As a Staff Data Scientist in Irvine, CA, you will design the modeling and evaluation approaches that others build on for a problem class, set validation strategy, and raise the modeling rigor of the teams around you while remaining deeply hands‑on.

• Design approach and modeling for problem classes such as medical imaging segmentation or multimodal patient‑state modeling and develop reference implementations.
• Apply advanced paradigms—including self‑supervised, contrastive, multi‑task learning, and cross‑modal fusion—to fit the problem.
• Define offline validation, calibration, and clinical performance evaluation strategies, including subgroup and fairness analysis in collaboration with Medical Affairs and Clinical Science.
• Establish reusable modeling patterns, evaluation harnesses, and documentation that meet regulatory submission expectations.
• Implement label‑efficient methods (active, semi‑supervised, weak supervision) and efficient training at scale using distributed training with Ray or PyTorch.
• Lead evaluation of emerging AI/ML for health research and decide what to adopt for IHFM problems.
• Provide technical leadership, mentor senior and mid‑level data scientists, and guide the research‑to‑productization handoff with AI/ML Engineers.
• Guide processes and tools for model performance analysis, optimization, and data accuracy, applying predictive modeling to improve outcomes (e.g., clinical trial experience).
• Partner with internal and external stakeholders to plan implementation, testing, training, and monitoring of machine learning models and present results to leadership.
• Drive processing of structured and unstructured data with data stewards, establish data governance practices, and integrate diverse data sources to enhance solutions.

Required: Bachelor’s degree in Computer Science, Engineering, Biostatistics or a scientific field plus 6years of experience in industry or education; or Master’s degree plus 5years; or PhD plus 2years. Relocation is not provided; candidates must reside within 50miles of Irvine, CA.

Preferred:
• Deep domain expertise in cardiac, hemodynamic, imaging, or physiological modeling.
• Recognized depth across multiple paradigms and architecture families, including self‑supervised and multimodal approaches.
• Depth in one or more data modalities (physiological modeling, medical imaging, or multimodal fusion) with calibration and uncertainty quantification.
• Ability to set modeling and validation standards that others follow and communicate decisions to clinical and regulatory partners.
• Fluency across the modeling stack (e.g., PyTorch, PyTorch Lightning, experiment tracking).
• Advanced generative or graph methods, federated learning methodology, and performance engineering for training (C++, CUDA, JAX, Deep Speed).
• Demonstrated technical leadership, mentorship, and a history of shaping clinical validation strategy and regulatory submissions for models.
• Recognized research contributions in AI/ML for health and experience with active learning or weak supervision to reduce clinical labeling cost.

Salary: For California (CA), the base pay range is $126,000 to $178,000 for highly experienced candidates. Final compensation will depend on qualifications and experience.

Edwards Lifesciences is an Equal Opportunity/Affirmative Action employer, including protected veterans and individuals with disabilities.

COVID Vaccination Requirement: All patient‑facing and in‑hospital positions require COVID‑19 vaccination. If hired into a covered role, proof of vaccination must be submitted unless a medical or religious accommodation is granted. This requirement does not apply in locations where it is prohibited by law.