The Object Detection and Tracking team at Zoox deals with the perception of all people and objects that can move. Your role is to work on the ML model team to develop detection and tracking models and to integrate them into the vehicle stack.
In this role, you will have access to the world's best sensor data and an incredible infrastructure for testing and validating your algorithms. We are creating new algorithms for detection, tracking, classification, and high-level scene understanding, and you could work on any (or all!) of these components.
In this role, you will...
Define on-vehicle architecture for producing the core tracking results from the Perception stack.
Assist with the implementation of core tracking results from the Perception stack
Work with both the model and data teams to develop a high-performance, efficient model that can run on a vehicle.
Work with Perception data, both on the input and output of machine learning models
Qualifications
BS or higher in Computer Science or a related degree
Familiarity with modern, Sparse-BEV Joint Detection and Tracking models.
Hands-on experience with production ML pipelines, including dataset creation, metrics, and optimization
Experience in Python, PyTorch, or a related ML framework
Bonus Qualifications
Experience with CUDA code and/or TensorRT
Strong mathematical skills and understanding of probabilistic techniques
Experience implementing tracking systems
