Clinical Imaging Platform Engineer

a2z Radiology AI • Boston, MA

2d • $68,000 - $18,000 • Hybrid

About The Position

We're building clinical AI that reads alongside radiologists. Our abdomen-pelvis CT triage device is FDA-cleared, and it's the first commercial system to simultaneously triage seven urgent conditions on abdomen-pelvis CT in the U.S. Backed by Khosla Ventures. Every model we train is limited by two things this role owns: the labels going in, and whether a radiologist can see and trust what comes out. Radiologist time is the most expensive input we have. A reader who clicks four times for something that should take one click costs us annotation throughput, which costs us model quality, which costs a patient a finding. That chain is short and real. The interface is the throughput. The other half is harder to see from outside. Generating labels isn't enough, you have to know if they're any good. Our annotation pipeline measures itself: race-free case claiming, per-annotator phase progression, batches seeded with known ground truth, other batches deliberately overlapped between readers, and agreement scored with per-lesion Dice across series that don't share a reconstruction geometry. That's measurement design, not CRUD.

Requirements

• Experience building something people used for hours a day and iterating on it after observing usage.
• Instinct to define metrics when asked about annotation quality, rather than describing processes.
• Comfort with coordinate systems and a preference for solving geometry issues accurately.
• Default to fail-closed security practices with patient data.
• Ability to disagree with a radiologist about software while deferring to their medical expertise.
• Product instinct.
• Measurement instinct.
• Comfort with hard geometry.

Nice To Haves

• Strong React/TypeScript with real performance work.
• Backend APIs and async experience.
• Experience with DICOM, Cornerstone3D, OHIF, or PACS.
• Experience with annotation tooling.
• AWS and Terraform experience.
• Segmentation or computer vision experience.
• Experience with inter-rater agreement and measurement design.
• Experience with regulated software (ISO 13485, IEC 62304, HIPAA).
• Experience with HTJ2K or progressive streaming.

Responsibilities

• Own the viewer, utilizing Cornerstone3D and VTK.js, including unified volume rendering with stack fallback, on-demand reformats in any plane, and progressive loading.
• Develop and maintain the annotation factory, including 3D mask storage, AI-assisted click-to-segment tools, classical annotation tools, and the evaluated pipeline around them.
• Define and implement annotation schemas with clinical judgment, including per-lesion-category schemas, gating by view/phase/slice, and conditionally required fields.
• Develop and manage the model output as a product surface, including a versioned sparse-RLE mask contract keyed by SOP Instance UID, and the necessary calculations for scaling model output to world-space contours.
• Manage the platform underneath, utilizing FastAPI on AWS, including per-study authorization, customer cohort isolation, and HIPAA §164.312(b) access trails.
• Become fluent in DICOM geometry to address hard bugs related to it.

Benefits

• Base salary
• Discretionary bonus
• Equity (for top candidates in Boston)
• Contractor or employee via an employer of record (for international remote)
• Same repositories, data, and review authority as US-based engineers (for international remote)

What This Job Offers

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