Senior Staff Machine Learning Engineer - Perception

About the Role

Our Perception team is responsible for using our sensor data to understand the complex and dynamic environments where we drive. In this role, you will have access to sensor data and infrastructure for testing and validating algorithms. We are creating new algorithms for segmentation, tracking, classification, and high-level scene understanding.

As a Senior Staff ML Engineer, you will lead the development of machine learning algorithms ranging from onboard autonomy to offboard autonomy and validation. You will collaborate closely with teams specializing in Prediction, Planning, Simulation, and Safety Validation, crossing team boundaries to prototype new approaches that influence long-term technical direction across multiple organizations.

Responsibilities

• Develop new algorithms to understand the scene around the robot, and how that scene evolves through time
• Build multi-modal foundation models for on-vehicle and offline applications
• Develop new algorithms to apply generative AI to simulation to improve the realism of offline validation systems
• Leverage large-scale machine learning infrastructure to discover new solutions and push boundaries
• Provide technical mentorship to the broader group of ML developers at Zoox
• Collaborate with engineers on Prediction, Planning, and Simulation to solve the autonomous driving problem in complex urban environments

Qualifications

• BS, MS, or PhD degree in computer science or related field
• Experience with training and deploying Deep Learning models on sensor data
• Experience with production Machine Learning pipelines: dataset creation, training frameworks, metrics pipelines
• Experience with modern computer vision techniques
• Strong mathematical skills and understanding of probabilistic techniques
• Fluency in C++ or fluency in Python with a basic understanding of C++
• Extensive experience with programming and algorithm design

Bonus Qualifications

• Publications in your field (CVPR, ICCV, RSS, ICRA preferred)
• Experience with autonomous robots
• Experience with real-time sensor fusion (e.g. LiDAR, camera, radar)
• Experience with novel pipelines and architectures for convolutional neural networks
• Experience with 3D data and representations (point clouds, meshes, etc.)