Senior Machine Learning Engineer, Multimodal Perception
Core
Architect, train, and optimize multi-task deep learning models for multi-modal sensor fusion, vehicle semantics, and signal detection to enable safe autonomous vehicle interaction.
Role type
Senior IC machine learning engineer (multimodal perception)
Builds
Multi-modal perception systems, automated data mining pipelines, and high-resolution vision architectures for the Waymo Driver.
Domain
Autonomous driving, computer vision, multi-modal sensor fusion
Deliverable
production ML models
Required skills
multi-modal sensor fusion, multi-task learning, transformer architectures, PyTorch, JAX, high-resolution vision architectures, spatial-temporal transformers, automated data curation, active learning, auto-labeling, model optimization for onboard inference
Preferred skills
multimodal foundation models, synthetic edge-case generation, failure triage, modern AI developer tools
Technologies
PyTorch, JAX, Transformers
Responsibilities
Architect and optimize multi-task deep learning models across multi-modal sensor streams; Build automated data mining pipelines and active learning loops; Develop high-resolution vision architectures and spatial-temporal transformer backbones; Profile and optimize models for efficient onboard accelerator inference
Seniority
Senior, hands-on IC