Research Scientist, Neural Reconstruction

Waabi Waabi · Robotics · Toronto, ON +3 · Remote · Autonomy & Algorithms

Research Scientist focused on developing next-generation neural scene-representation and reconstruction algorithms for autonomous transportation, transforming sensor data into digital worlds. This role involves fundamental and applied research in 3D/4D neural reconstruction, dynamic scene reconstruction, and multi-sensor learning, directly powering simulation and rendering systems.

What you'd actually do

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

Skills

Required

  • Python
  • PyTorch
  • JAX
  • distributed training
  • generative models
  • predictive models
  • 3D/4D neural reconstruction
  • 3DGS/NeRF
  • neural scene representation
  • generalizable reconstruction models
  • dynamic scene reconstruction
  • multi-sensor scene representation learning

Nice to have

  • translate research into production-quality code
  • measurable product impact
  • first-author publications
  • camera
  • LiDAR
  • large-scale driving datasets
  • graphics
  • geometry
  • rendering systems
  • simulation

What the JD emphasized

  • Ph.D. in Computer Vision, Machine Learning, Robotics, or a related field or equivalent research experience pushing the boundaries of a technical field.
  • Expert-level Python & PyTorch (or JAX) skills
  • built generative or predictive models of the physical world with scale and efficiency in mind for real-world applications
  • Proven ability to translate research into production-quality code and measurable product impact.
  • Demonstrated first-author publications in top-tier venues on topics such as: 3DGS / NeRF / neural rendering, 3D / 4D reconstruction, Generalizable reconstruction, Geometry-aware or multi-sensor representation learning

Other signals

  • neural reconstruction
  • 3D/4D neural reconstruction and rendering
  • 3DGS/NeRF
  • neural scene representation
  • generalizable reconstruction models