AI Neural Radiance Field Engineer

Prixel Labs

Remote · $160k – $200k / year · Full-time · Posted 4 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

Neural radiance fields changed what's possible in 3D reconstruction — but the original NeRF pipeline takes 12 hours to train and another 2 to render a single frame. If you want NeRF-quality scene reconstruction in a real-time product, you need to make it 1000x faster without sacrificing visual quality. We've been working on this problem for two years, and we're close. Our approach combines hash-based feature grids with a distillation pipeline that transfers quality from a high-fidelity NeRF to a real-time baked representation. The result trains in under 10 minutes and renders at 60fps on a mobile GPU. What's missing is robustness: the system degrades on scenes with reflective surfaces, fast motion, or sparse camera coverage. You'll join a research engineering team of three tackling these failure modes. Your work will ship in our photogrammetry SaaS used by 800 architecture firms and real estate companies. If you've published on NeRF, Gaussian splatting, or 3D scene representation, we want to hear from you.

Fully remote.

Responsibilities

Improve NeRF robustness for reflective surfaces, motion blur, and sparse-view inputs
Optimize training speed and memory footprint for mobile GPU deployment
Implement and evaluate recent scene representation methods like Gaussian splatting
Build evaluation benchmarks comparing reconstruction quality across scene types
Collaborate with product team to translate research into user-facing quality guarantees
Write technical reports on methods and results for partner communications

Requirements

5+ years in 3D computer vision or neural rendering
Deep familiarity with NeRF, Gaussian splatting, or related scene representation methods
Strong PyTorch skills and GPU programming knowledge
Publications or significant open-source contributions in 3D vision preferred
Experience shipping research into production products