Staff, Machine Learning Engineer - BEV/Multi-Modal Perception
Core
Lead development of next-generation BEV and multi-modal perception models that unify camera, LiDAR, and radar data for autonomous truck perception.
Role type
Staff Machine Learning Engineer (BEV/Multi-Modal Perception)
Builds
Foundational perception models and large-scale training workflows for autonomous driving stacks
Domain
Autonomous driving / 3D perception / Multi-modal sensor fusion
Deliverable
production ML models
Required skills
BEV modeling, 3D scene understanding, multi-view fusion, multi-modal sensor fusion (camera/LiDAR), Python, PyTorch or TensorFlow, large-scale distributed training, experiment management, technical leadership, model innovation
Preferred skills
Autonomous driving production experience, MLOps, Ray, 3D labeling, sensor simulation, top-tier publications (CVPR/ICCV/NeurIPS)
Responsibilities
Define technical roadmap for BEV perception models, design multi-modal architectures, develop foundational models, own large-scale training workflows, advance model robustness, establish evaluation frameworks, collaborate with sensor calibration and mapping teams, mentor ML engineers, explore self-supervised learning and foundation models
Seniority
Staff, technical leadership & mentorship
