Principal Machine Learning Engineer (Reconstruction / Quantitative Imaging)
San Francisco • FullTime
Posted 2mo ago
Job Location
San Francisco
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Machine Learning Engineer
About the job
We are seeking a Principal Machine Learning Engineer to partner with medical image reconstruction scientists and engineers. In this role, you will build ML components to enhance reconstruction quality, speed, robustness, and quantitative accuracy. You will define training and evaluation pipelines, datasets, and metrics aligned with user needs and design requirements. A key part of this role involves productionizing models, focusing on inference performance, reproducibility, monitoring for drift and regressions, and implementing safe fallbacks. You will also collaborate on hybrid algorithms that integrate physics with learned priors, denoisers, learned regularizers, and quality estimation, and contribute to building tooling for rapid experimentation and rigorous verification of algorithm changes.
Responsibilities
- Build ML components to improve medical image reconstruction quality, speed, robustness, or quantitative accuracy.
- Define training/evaluation pipelines, datasets, and metrics.
- Productionize models, focusing on inference performance, reproducibility, monitoring, and safe fallbacks.
- Collaborate on hybrid algorithms incorporating physics and learned components.
- Build tooling for rapid experimentation and verification of algorithm changes.
Requirements
- Strong applied ML experience.
- Comfort with signal processing, imaging, or adjacent domains.
- Ability to move between research prototypes and production systems.
- Strong evaluation discipline (metrics, ablations, data leakage avoidance, reproducibility).
- Demonstrated track record of applying ML to physics-based or inverse problems.