alt Hacker NewsGameBrain AI (https://www.gamebrain.com/) | Staff Computer Vision Architect (BEV & Spatial Perception) | Remote + Troy, MI (1-2 week paid travel per quarter) | Full-time
I’m the CTO at GameBrain. I previously spent 6 years helping to build autonomous vehicle perception stacks at Cruise and Ford.
At Gamebrain, we’re applying SOTA computer vision models to help teams dramatically accelerate game prep and scouting, saving days of manual repetitive work per week to give coaches and analysts massive leverage over their opponents. One of the biggest unlocks: legal access to real, high-quality sports data through deep relationships in the sports industry. Anyone who has built production CV systems knows how rare, and how valuable, that is.
I'm hiring a Staff Deep Learning Computer Vision Engineer. If you've spent your career designing, training, and scaling complex perception stacks - in AV, robotics, AR/VR, or anywhere that demands rigorous 3D spatial reasoning and multi-view fusion - this role was made for you.
The engineering problems: automated homography with unknown camera intrinsics/extrinsics, temporal tracking through heavy occlusion, and multi-view sensor fusion.
We do not want a 50-person engineering org. We want a highly elite and specialized team to outperform massive legacy organizations.
You will own the zero-to-one architecture of our perception pipeline. We just hired an Active learning expert from the self driving car space who you will work closely with.
You must deeply understand projective geometry, representation learning vs. pixel reconstruction, and how to build robust active learning loops.
We compensate at parity with tier-one AV companies (Tesla, Waymo) for this role.
Location: Anywhere. Required to come to Troy 1-2 weeks per quarter (which we will pay for). Required to take meetings when needed during Eastern Time hours.
If you are a high-leverage operator who wants to build complex spatial architecture that actually sees production on day one, apply below: