As a Research Scientist in World Models, you will develop algorithms and productionize the next generation of World Simulation models that can reason about complex, dynamic 4D environments with minimal supervision. Your work will directly power Waabi Worldβs ability to comprehend the 4D physical world, simulate traffic participants and generate realistic safety-critical scenarios at scale.
You will conduct fundamental and applied research in generative and predictive world-modeling (e.g., latent diffusion, video generation models, 3D Gaussian splatting, NeRF) on multi-sensor multi-modal data of driving scenes. 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, ICRA, SIGGRAPH). Mentor junior scientists and interns; foster a culture of scientific rigor and rapid experimentation. Stay on top of emerging advances in generative AI, differentiable rendering, knowledge distillation/compression, and robotics.