AI Wearable ECG Arrhythmia Detection Engineer

Orbio AI

Remote · $160k – $200k / year · Full-time · Posted 4 weeks ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Roughly 40,000 patients wear one of our partner patches every night, and the alerts your models raise will reach a cardiologist before breakfast. Orbio AI builds the detection layer behind single-lead ECG wearables used in post-discharge cardiac monitoring programs. Our current atrial fibrillation classifier is solid, but it struggles with motion artifacts and misses short runs of ventricular tachycardia that clinicians care about most. In this role you'll redesign the signal pipeline and the model family behind it, working from a labelled archive of more than two million annotated strips. We read papers, we argue about them in a weekly journal club, and we expect you to bring ideas from the literature into production rather than leave them in a notebook. Success here means fewer false alarms for overworked monitoring nurses and fewer missed events for patients.

Fully remote.

Responsibilities

Own the arrhythmia detection model from signal preprocessing to the deployed inference service
Design robust handling for motion artifacts, lead-off periods and low signal quality
Run retrospective validation studies with our clinical science team before every release
Translate recent research on 1D convolutional and transformer ECG models into tested experiments

Requirements

Deep experience training models on physiological time-series such as ECG, PPG or EEG
Fluent in PyTorch and comfortable writing custom data loaders for irregular signals
Solid grounding in sensitivity, specificity and calibration for clinical settings
Experience working under FDA or CE medical device processes is a strong plus