Research Scientist, Neural Reconstruction

About the role

Waabi is the leader in Physical AI, building autonomous transportation solutions. As a Research Scientist in Neural Reconstruction, you will develop next‑generation neural scene‑representation and reconstruction algorithms that transform sparse, noisy driving data into realistic, controllable digital worlds.

Key responsibilities

• Conduct fundamental and applied research in neural reconstruction, including 3DGS/NeRF, dynamic scene reconstruction, feed‑forward reconstruction, and multi‑sensor scene representation learning.
• Build scalable reconstruction and simulation systems for dynamic urban scenes, covering 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 such as CVPR, ICCV, NeurIPS, ICLR, ICRA, and SIGGRAPH.
• Mentor junior scientists and interns, fostering a culture of scientific rigor and rapid experimentation.

Required profile

• Ph.D. in Computer Vision, Machine Learning, Robotics, or a related field, or equivalent research experience.
• Expert‑level Python and PyTorch (or JAX) skills with strong software‑engineering fundamentals and experience in distributed training.
• Proven ability to build generative or predictive models of the physical world with scale and efficiency for real‑world applications.
• Experience working in a close‑knit team of researchers and engineers with strong communication skills.

Required skills

• Python
• PyTorch
• JAX
• Distributed training