Advance Waabi World through generative AI, video prediction, and controllable simulation. Help develop models for autonomous trucks and robotaxis.
Waabi is seeking a Research Scientist to develop and productionize large-scale world models for autonomous transportation. The work includes latent diffusion, autoregressive, flow-matching, and multimodal foundation models. You will also explore LLM, VLM, and VLA methods for scene understanding, reasoning, and control across dynamic driving environments.
Key Responsibilities: Develop controllable generative scenario models
Research latent diffusion and flow-matching approaches
Apply LLM, VLM, and VLA methods to driving scenes
Collaborate on distributed training and rendering integration
Track advances in generative AI and robotics
Requirements: Ph.D. or equivalent research experience in computer vision, machine learning, or robotics
Expert Python and PyTorch or JAX implementation skills
Experience with distributed training and software engineering
Expertise developing efficient physical-world generative models
Ability to collaborate closely with researchers and engineers
Bring generative AI expertise, controllable simulation knowledge, and robust implementation skills to Waabi’s world-modeling research.