Principal Machine Learning Engineer (Reconstruction / Quantitative Imaging)

Midjourney • San Francisco, CA

3d

About The Position

This role involves partnering with medical image reconstruction scientists and engineers to develop Machine Learning (ML) components aimed at enhancing the quality, speed, robustness, and quantitative accuracy of image reconstruction. The position requires defining training and evaluation pipelines, datasets, and metrics that align with user needs and design requirements. A key aspect is the productionization of models, focusing on inference performance, reproducibility, monitoring for drift and regressions, and implementing safe fallbacks. Collaboration on hybrid algorithms that integrate physics with learned priors, denoisers, regularizers, and quality estimation is also expected. The role includes contributing to the development of tooling for both rapid experimentation and rigorous verification of algorithm changes.

Requirements

• Strong applied ML experience.
• Comfort with signal processing/imaging or adjacent domains.
• Ability to move fluidly between research prototypes and production-quality systems.
• Strong evaluation discipline: metrics, ablations, data leakage avoidance, and reproducibility.
• Demonstrated track record of applying ML to physics-based or inverse problems (e.g., shipped projects, portfolio, or publications).

Nice To Haves

• ML for imaging/inverse problems (or adjacent) with strong evaluation discipline and comfort with GPU performance constraints.
• Pragmatic production mindset: reproducible training/inference, regression testing, and safe deployment in high-stakes contexts.
• Background in computational physics or scientific computing.
• Leverage ML-based methods such as PiNNs and Neural Operators to solve partial differential equations arising in ultrasound simulation and imaging.
• Experience in Agentic-SciML is a plus.
• Hands-on experience with data curation for ML: building datasets from messy, real-world sources, defining ground truth, and managing labeling or simulation pipelines.
• Background in data assimilation: combining observations with physics-based models (Kalman filtering, variational methods, ensemble approaches, or learned variants).

Responsibilities

• Partner with medical image reconstruction scientists/engineers to build ML components that improve reconstruction quality, speed, robustness, or quantitative accuracy.
• Define training/evaluation pipelines, datasets, and metrics that map to user needs and design requirements.
• Productionize models, focusing on inference performance, reproducibility, monitoring for drift/regressions, and safe fallbacks.
• Collaborate on hybrid algorithms, incorporating physics and learned priors, denoisers, learned regularizers, and quality estimation.
• Help build tooling for rapid experimentation as well as rigorous verification of algorithm changes.

What This Job Offers

• Job Type: Full-time
• Career Level: Principal
• Education Level: No Education Listed