Lead Trajectory ML Engineer for Autonomous Driving

Zoox; Foster City (CA); On-site; USD 242,000 - 349,000; Full time

Benefits offered by this job

Paid time off

Zoox Stock Appreciation Rights

Amazon RSUs

Health insurance

Long-term disability insurance

Life insurance

Job summary

Zoox is seeking a Learned Trajectory Machine Learning Engineer to develop deep learned models that generate driving trajectories for autonomous vehicles. You will collaborate with Planner and Perception teams to advance vehicle behavior, using imitation and reinforcement learning to produce safe and efficient driving plans.

The role involves leveraging large-scale ML infrastructure, crafting metrics, and working across perception, planning, and simulation teams to solve complex urban driving

Qualifications

• Advanced degree in CS or related field
• Experience with training and deploying transformer-based models and reinforcement learning
• Fluency in Python and basic understanding of C++
• Strong mathematical, programming, and algorithm design skills

Responsibilities

• Develop new deep learning models that use imitation learning and reinforcement learning to generate driving plans for autonomous vehicles
• Leverage large-scale ML infrastructure to discover new solutions
• Develop metrics and tools to analyze errors and understand improvements of the systems
• Collaborate with Perception, Planning, and Simulation teams to solve the autonomous driving problem in urban environments

Skills

Python

Transformer models

Reinforcement learning

ML pipelines

Mathematics

Education

BS/MS/PhD in Computer Science or related field

Tools

C++ basics

Job description

Zoox is seeking a Learned Trajectory Machine Learning Engineer to develop deep learned models that generate driving trajectories for autonomous vehicles. You will collaborate with Planner and Perception teams to advance vehicle behavior, using imitation and reinforcement learning to produce safe and efficient driving plans.

The role involves leveraging large-scale ML infrastructure, crafting metrics, and working across perception, planning, and simulation teams to solve complex urban driving