Deep Learning Engineer

Trivon Data

Remote · $130k – $160k / year · Contract · 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

Fast-moving team. Hard problems. No meetings before noon. We're building a real-time sports analytics platform that uses computer vision to track player movements, predict game outcomes, and generate automated highlight reels. Our models process 60fps video feeds from 20+ simultaneous camera angles. We need a deep learning engineer on a 12-month contract to help us build our next-gen player tracking models. You'll work on multi-object tracking, pose estimation, and action recognition — all at inference speeds that keep up with live broadcasts. The infrastructure is in place. The data is labeled. What we need is someone who can push model accuracy on the hardest sequences: occlusions, camera transitions, and fast-moving plays. If that sounds like fun, let's talk.

Fully remote.

Responsibilities

Design and train multi-object tracking models for live sports video
Optimize inference pipelines for real-time performance at 60fps
Build evaluation benchmarks for tracking accuracy on challenging sequences
Collaborate with the video engineering team on camera calibration and feed preprocessing
Deliver weekly progress reports with quantitative results