AI Sign Language Recognition Engineer

Vordex Tech

Remote · $100k – $130k / year · Full-time · Posted 5 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

460 million people worldwide have disabling hearing loss, and the tools that serve them in digital interfaces are embarrassingly underdeveloped. Automatic sign language recognition — converting hand gestures and facial expressions into text — could transform accessibility for deaf and hard-of-hearing users across video calls, kiosks, and consumer devices. The technology exists in research; production-grade, real-time, multi-signer systems do not. We're building the first production sign language recognition API supporting American Sign Language and British Sign Language, with 8 additional languages in the pipeline. The core computer vision system achieves 89% word-level accuracy in controlled conditions; the challenge is robustness in the real world — different lighting, backgrounds, signer appearances, and the natural variation in how individuals sign. You'll improve the recognition pipeline's robustness, build the data augmentation strategy that reduces dependence on controlled training conditions, and develop the real-time optimization that makes the system usable on consumer hardware without a cloud latency penalty.

Fully remote.

Responsibilities

Improve sign language recognition robustness across lighting, background, and signer variation
Design data augmentation strategies that simulate real-world signing conditions
Optimize the recognition pipeline for real-time inference on consumer hardware
Build evaluation frameworks using native signer reviewers as ground truth
Expand the training dataset through synthetic data generation and community partnerships
Collaborate with Deaf community advisors on accuracy and cultural appropriateness

Requirements

3+ years in computer vision engineering with video or gesture recognition experience
Experience with pose estimation, hand keypoint detection, or action recognition
Strong PyTorch skills and familiarity with transformer-based video models
Understanding of real-time optimization for edge deployment
Sensitivity to accessibility contexts and willingness to work with community advisors