Neural Reconstruction Scientist - Remote 3D World Rendering

Waabi; Toronto; On-site; CAD 214,000 - 371,000; Full time

Benefits offered by this job

Equity awards

Health benefits

Dental & Vision

Unlimited vacation

Flexible hours

Work from home

Catered meals

Team events

Job summary

Waabi is seeking a Research Scientist in Neural Reconstruction to advance 3D/4D scene understanding using NeRF, 3DGS, and neural rendering. You will transform sparse driving data into realistic digital worlds and integrate models into scalable training and rendering pipelines.

You will publish at CVPR/ECCV/NeurIPS and mentor junior scientists while collaborating with simulation engineers to push the boundaries of perception, geometry, and multi-sensor fusion.

Qualifications

• PhD or equivalent research experience in CV/ML/Robotics.
• Expert-level Python & PyTorch (or JAX); distributed training experience.
• Experience building generative or predictive models of the physical world at scale.
• Team player with strong communication to deliver projects.

Responsibilities

• Conduct fundamental and applied research in neural reconstruction, including 3DGS / NeRF, dynamic scene reconstruction, feed-forward reconstruction, multi-sensor representation learning.
• Build scalable reconstruction and simulation systems for dynamic urban scenes, including vehicles, background, lighting, and long-range structure.
• Collaborate with simulation engineers to integrate models into large-scale, distributed training and rendering pipelines.
• Publish high-impact research at top conferences (CVPR, ECCV, ICCV, NeurIPS, ICLR, SIGGRAPH).
• Mentor junior scientists and interns; foster a culture of scientific rigor and rapid experimentation.
• Stay current with advances in neural rendering, 3D representation learning, differentiable rendering, and scalable reconstruction systems.

Skills

Python

PyTorch

Distributed training

Research collaboration

Education

PhD in Computer Vision / ML / Robotics

Tools

JAX

Job description

Waabi is seeking a Research Scientist in Neural Reconstruction to advance 3D/4D scene understanding using NeRF, 3DGS, and neural rendering. You will transform sparse driving data into realistic digital worlds and integrate models into scalable training and rendering pipelines.

You will publish at CVPR/ECCV/NeurIPS and mentor junior scientists while collaborating with simulation engineers to push the boundaries of perception, geometry, and multi-sensor fusion.