Machine Learning Engineer, Perception Modeling

Apply ML techniques to build multi-modal sensor fusion architectures and spatial-temporal representations for perception tasks such as object detection, tracking, occupancy, and semantic segmentation.
Create scalable data and model training pipelines that run on distributed compute, including pre-training and post-training workflows.
Design and implement distributed fine-tuning to enable multiple developers to iteratively improve models while protecting production performance.
Develop and maintain model evaluation recipes and metrics to measure and improve pre-trained and fine-tuned models.
Collaborate with downstream teams to optimize models for onboard and offboard hardware and ensure robust real-world deployment.
Ideal candidates have 3+ years in ML/CV, strong Python skills, and experience with PyTorch or JAX; a relevant degree or equivalent deep learning experience; C++ is a plus.