Senior iOS Engineer

About Sonari

Sonari is a well-funded startup and the world's first company to deploy AI-powered ultrasound in professional sports, converting a fast, portable scan into objective data on an athlete's tissue health, performance and endurance over time. We're working toward an unprecedented goal: predicting soft-tissue and non-contact injuries.

Our technology is grounded in peer-reviewed research. We're backed by a global investment firm ($70B+ AUM) and partnered with a Major League Baseball team and a Premier League club. Our aim is to put this capability in the hands of every sports organization worldwide, from championship rosters to academies where the next generation is emerging.We're mission-driven and looking for like-minded top engineers who want to build at the intersection of AI, medical imaging and sports.

The role

You own the iPad app: the capture experience and UX, the real-time imaging pipeline from a handheld ultrasound probe, on-device ML inference, and the secure, de-identified upload path to the backend. The app is the point of capture and the edge of the whole system — everything downstream starts with the images it captures. You'll work in a fast-paced, hands-on environment, reporting directly to the CTO.

What you'll work on

• A native iPad app (Swift / SwiftUI, iOS 17+) with a clean, testable separation between UI, imaging, and services. We lean on modern Swift Concurrency; the exact architecture is yours to shape.
• Capture UX & UI. Design and build the real-time capture experience — navigation/guidance overlays, quality prompts, and capture confirmation — in close collaboration with design and the clinical team. Good UX is what lets a non-expert user capture a good image, so this is core to the role, not an afterthought.
• Live ultrasound imaging from a handheld ultrasound probe via its vendor imaging SDK - typically BLE discovery → joining the probe's Wi-Fi → streaming B-mode imaging. The imaging boundary sits behind a protocol so the app develops and tests in the simulator against a mock imaging source, with the device-only vendor framework isolated behind a single adapter.
• On-device ML. Run on-device (e.g. CoreML) navigation and segmentation models to recognize views, score image quality, and drive the guidance overlays in real time.
• Two capture streams. A user-confirmed diagnostic stream and a consent-gated background sampling stream for model improvement — each handled appropriately.
• Secure upload to the cloud. Upload captured data to the cloud securely and reliably, ensuring it stays de-identified — no athlete-identifying information (name, DOB, operator, comments) ever leaves the device in image metadata, keys, filenames, logs, or crash reports; images carry only UUIDs and a numeric research ID.
• Secure device auth, with tokens held in the Keychain.

Required skills

• Strong Swift and SwiftUI, with real experience shipping iPad/iOS apps — including a good sense for UX/UI on touch devices.
• Swift Concurrency: async/await, actors, structured concurrency — you can reason about a real-time streaming pipeline without data races.
• A testable, decoupled architecture; comfort developing against mocks and abstractions rather than requiring hardware to make progress.
• On-device ML integration (e.g. CoreML): loading models, running them on image frames, and handling outputs for overlays.
• Networking against REST APIs (secure uploads, token auth) and Swift Package Manager for dependency and shared-contract consumption.
• Testing with XCTest; a habit of keeping simulator builds green.
• AI-assisted development as a daily habit: you use tools like Claude Code, Codex or Cursor to move faster, and you have the judgment to know when their output is right and when it isn't.

Nice to have

• Hardware / peripheral SDK integration — BLE / CoreBluetooth, Wi-Fi peripheral joining, or streaming-media pipelines.
• Prior work with ultrasound, medical devices, or imaging apps.
• Strong visual/interaction design instincts, or experience partnering closely with designers.
• XcodeGen or other project-generation / reproducible-project tooling.
• Experience with de-identified / regulated data handling on device (Keychain, excluding data from backups, no-identifier logging).
• Metal / Accelerate or performance tuning for real-time image display.

Tech stack you'll touch

Swift · SwiftUI · Swift Concurrency · on-device ML (CoreML) · a handheld-ultrasound-probe SDK (device-only) · BLE + Wi-Fi networking · Swift Package Manager · XcodeGen · XCTest · secure cloud uploads · a shared Swift-package contract library generated from the platform's API/schema definitions.

How this role fits the team

You'll be one of the first members of our engineering team. The Machine Learning Engineer trains and packages the on-device models you run; the Full-stack Engineer operates the backend your uploads land in. The seams between you - the imaging-source protocol, the frame/metadata types, and the upload API - are defined as shared, versioned contracts so the parts of the system can evolve independently.

Pay: $150,000.00 - $180,000.00 per year

Benefits:

• Dental insurance
• Health insurance

Work Location: Hybrid remote in Cambridge, MA 02142