Computer Vision Engineer — Medical Imaging QA

NordBot AI

Hybrid (Toronto, CA) · $118K – $142K · Full-time · Posted 6 months 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

Our software checks imaging quality before a study moves deeper into the radiology workflow. We are not trying to diagnose disease. We are trying to catch bad positioning, incomplete series, and acquisition artefacts early enough that staff can do something about them. That makes this role more operational than academic. We need a computer vision engineer who is comfortable with medical-data discipline, clear evaluation standards, and product work where reliability matters more than novelty.

Responsibilities

Develop and improve models that detect acquisition-quality issues in radiology workflows
Work with product and domain specialists to define error categories that matter operationally
Build evaluation processes that reflect real imaging-centre usage and acceptable error tolerances
Support deployment readiness through monitoring plans and clear documentation
Contribute to data curation feedback loops with annotation and clinical operations teams

Requirements

4+ years of computer vision engineering with experience in medical, industrial, or other high-precision domains
PyTorch for model training and evaluation
Computer Vision experience with classification, anomaly detection, or image quality assessment
NumPy for efficient preprocessing and analysis workflows
Scikit-learn for baseline modelling, calibration, and evaluation support
Docker for reproducible training and deployment pipelines