Staff, Machine Learning Engineer - BEV/Multi-Modal Perception

What you'll do

• Define the technical roadmap and develop BEV perception models for tasks such as detection, segmentation, and scene understanding.
• Design multi-modal sensor-fusion architectures and own large-scale model training and evaluation workflows.
• Improve model robustness, mentor ML engineers, and collaborate with calibration, mapping, and fusion teams.

What they ask for

• 10+ years of experience in deep learning for perception, 3D vision, and/or autonomous systems.
• M.S. or Ph.D. in a related field, or equivalent practical experience.
• Expertise in BEV modeling, 3D scene understanding, and multi-view fusion; strong multi-modal sensor-fusion background, particularly camera and LiDAR.
• Proficiency in Python and PyTorch or TensorFlow; experience with large-scale data pipelines and distributed training.

Nice to have

• Autonomous driving or robotics perception experience in production; MLOps or Ray experience.
• Experience with BEV architectures, LiDAR-vision fusion, spatial-temporal modeling, or 3D labeling, calibration, and sensor simulation.

Pay

$215,500 — $258,600 USD (total compensation; pay range; base salary not specified)

Tools

BEV, camera, LiDAR, radar, HD maps, Python, PyTorch, TensorFlow

AI focus

Develops BEV and multi-modal perception models, including large-scale training, sensor fusion, robustness, and exploration of self-supervised learning, pretraining, and foundation models for 3D perception.