Staff Data Scientist at Edwards Lifesciences

Compensation

$126,000 – $178,000/yr

Setup: Hybrid
Location: Irvine, California
Type: Full-time
Level: Principal

Description

Edwards Lifesciences is seeking a Staff Data Scientist to join their Implantable Heart Failure Management (IHFM) AI, Product and Platforms organization. Based in Irvine, CA, the role involves designing and building software and data products for clinicians and patients, focusing on advancing patient care through innovative technology. The ideal candidate will contribute to developing modeling and evaluation approaches, setting validation strategies, and mentoring junior data scientists.

Required Skills

PyTorch
PyTorch Lightning
experiment tracking
generative methods
graph neural networks
federated learning
Performance engineering
C++
CUDA
JAX
DeepSpeed

Additional Information

Minimum Education: Bachelor's in Computer Science, Engineering, Biostatistics or Scientific field or Master's.
Required Previous Experiences: 6 years of experience including either industry or academic background, or 5 years with a Master's, or 2 years with a PhD.
Preferred Qualifications: 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) and in calibration and uncertainty quantification.
The ability to set modeling and validation standards that others follow, and to represent modeling decisions to clinical and regulatory partners.
Fluency across the modeling stack (for example, PyTorch, PyTorch Lightning, and experiment tracking) sufficient to set team practice.
Advanced generative or graph methods (diffusion models, graph neural networks), or federated learning methodology.
Demonstrated technical leadership and mentorship.
Performance engineering for training (C++, CUDA, JAX, or DeepSpeed).
A history of shaping clinical validation strategy and regulatory submissions for models.
Recognized research contributions in AI/ML for health.
Active learning or weak supervision to reduce clinical labeling cost.