AI Point Cloud Segmentation Engineer

Prixel Labs

Remote · $130k – $160k / 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

LiDAR scanners capture buildings, construction sites, and infrastructure as dense point clouds — billions of 3D points that represent every surface, pipe, beam, and wire. Converting these raw scans into labeled BIM models takes skilled technicians 40 hours per scan. Our segmentation system automates the classification: identifying walls, floors, structural elements, MEP components, and furniture from the point cloud alone. The challenge is scale and diversity. A scan of a hospital wing contains 500 million points with 200+ object categories. A construction site scan has occluded surfaces, temporary structures, and objects that don't exist in any training dataset. You'll build segmentation models that handle this diversity while maintaining the precision that architects and engineers require — a misclassified structural beam isn't just an error; it's a safety risk. The 3D vision team is five engineers. You'll be the senior engineer who drives the segmentation architecture, designs the evaluation methodology, and ensures our models generalize across building types, scanner hardware, and scan conditions.

Fully remote.

Responsibilities

Design point cloud segmentation architectures for architectural and infrastructure scans
Handle 500M+ point clouds with 200+ object categories
Build evaluation frameworks measuring segmentation precision for BIM applications
Improve generalization across building types, scanners, and scan conditions
Optimize inference for large-scale point clouds within practical time budgets
Set technical direction for 3D segmentation research and production

Requirements

5+ years in 3D computer vision with point cloud experience
Experience with point cloud segmentation architectures: PointNet++, MinkowskiNet, or similar
Strong PyTorch skills for 3D model development
Understanding of AEC domain requirements and BIM concepts
Track record of shipping 3D vision systems to production