Multimodal World Model Scientist for Autonomous Driving

Kodiak; Mountain View (CA); On-site; USD 190,000 - 250,000; Full time

Benefits offered by this job

Equity and annual bonuses

Medical, Dental, Vision plans

Flexible PTO and paid holidays

Dog-friendly office in Mountain View

Free lunch and kitchen amenities

401(k) and commuter benefits

Job summary

Kodiak Robotics, Inc. in Mountain View, CA, is seeking a World Model Research Scientist to lead generative world models for autonomous driving.

You will design and train multi-sensor, multi-view models conditioned on actions, 3D scene context, and text, driving scalable closed-loop training and evaluation. The role requires a PhD in CS/AI/Robotics, strong publication record in diffusion/video synthesis, and proficiency with Python and PyTorch, with experience in distributed training and neural

Qualifications

• PhD in Computer Science, AI, Robotics, or a related field with a focus on generative modeling, neural rendering, or video synthesis.
• Strong publication record or demonstrated contributions in diffusion models, video generation, neural radiance fields, or 3D-aware generative models.

Responsibilities

• Design and train generative world models that synthesize realistic multi-camera video and LiDAR conditioned on ego trajectories, 3D scene context, and text.
• Research and implement conditional diffusion architectures for driving, including spatiotemporal attention, latent space design, and action-conditioned generation.
• Develop techniques for multi-view geometric consistency in generated outputs using neural rendering, cross-view attention, and 3D-aware generative approaches.
• Build methods for joint multimodal generation that maintain cross-sensor consistency between camera, LiDAR, and radar outputs.
• Design evaluation frameworks that measure world model quality beyond pixel-level metrics, including scenario fidelity and autoregressive stability.
• Scale training pipelines to learn from thousands of hours of real-world driving data across multiple sensor modalities.

Skills

Generative models

Diffusion models

Neural rendering

Video synthesis

Multimodal sensing

Distributed training

Cognition of 3D scenes

Education

PhD in CS, AI, Robotics

Tools

PyTorch

Job description

Kodiak Robotics, Inc. in Mountain View, CA, is seeking a World Model Research Scientist to lead generative world models for autonomous driving.

You will design and train multi-sensor, multi-view models conditioned on actions, 3D scene context, and text, driving scalable closed-loop training and evaluation. The role requires a PhD in CS/AI/Robotics, strong publication record in diffusion/video synthesis, and proficiency with Python and PyTorch, with experience in distributed training and neural