Research Scientist, Neural Reconstruction

What you'll do

• Research neural reconstruction, including 3DGS/NeRF, dynamic and feed-forward reconstruction, and multi-sensor scene representation learning.
• Build scalable reconstruction and simulation systems and integrate models into distributed training and rendering pipelines.
• Publish research, mentor junior scientists and interns, and collaborate with simulation engineers.

What they ask for

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

Nice to have

• Translating research into production-quality code with measurable product impact; first-author publications in top-tier venues.
• Experience with camera, LiDAR, maps, and large-scale driving datasets; background in graphics, geometry, rendering systems, or simulation.

Pay

$155,000 - $269,000 USD (base salary)

Tools

Python, PyTorch, JAX, 3DGS, NeRF

AI focus

Research and develop neural scene-representation, reconstruction, and rendering models for recovering geometry and dynamics from sensor data and creating realistic simulation environments.