AI Motor Impairment Interface Adaptation Engineer

Vordex Tech

Remote · $100k – $130k / year · Full-time · Posted 3 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 mission is to make every interface usable regardless of physical ability. This role focuses on the users our platform currently serves worst: people relying on switch access, eye-tracking, or limited range-of-motion input devices. You will build models that predict intended actions from noisy, imprecise input signals, dramatically reducing the number of interactions needed to complete common tasks. You'll partner closely with our accessibility research team and a panel of users with motor impairments who test every release before it ships, so your models are validated against real usage, not synthetic benchmarks.

Fully remote.

Responsibilities

Build intent-prediction models that reduce required interactions for motor-impaired users
Collaborate with our user testing panel to validate models against real usage patterns
Adapt existing interface components to support switch access and eye-tracking input
Analyze interaction logs to identify where current predictions fail users most
Document accessibility impact of each model iteration for the product team

Requirements

3+ years building ML-driven product features
Strong Python and TensorFlow skills
Genuine interest in accessibility and assistive technology
Comfortable incorporating qualitative user feedback into quantitative model decisions