Senior ML Engineer: Autonomous Driving Behavior Models

Front Door Defense; Foster City (CA); On-site; USD 254,000 - 366,000; Full time

Job summary

Zoox is seeking a Senior / Staff Machine Learning Engineer to develop and deploy behavior models for road users within the simulation stack in Foster City, CA. The role focuses on learning driving agent behaviors using imitation and reinforcement learning, enabling realistic, controllable agents for testing the autonomous driving system.

You will work on large-scale ML pipelines, transformer architectures, and generative models (diffusion/autoregressive) to predict and plan ego-vehicle actions,

Qualifications

• PhD in CS or related field with 4+ years of relevant experience, or a master's with 7+ years.
• Experience in planning, prediction, reinforcement learning, imitation learning, or generative modeling (diffusion, autoregressive models).
• Experience with training and deploying transformer-based model architectures.
• Experience with production ML pipelines: dataset creation, training frameworks, metrics pipelines.
• Fluency in Python ML frameworks and a basic understanding of C++.

Responsibilities

• Develop new deep learning models that use imitation learning and reinforcement learning to generate driving plans for human-like driving agents.
• Estimate the quality of driving plans along safety, progress, comfort and realism.
• Build generative behavior models (autoregressive, diffusion) conditioned on scenario intent for targeted stress-testing.
• Leverage compute, infrastructure and data to push the field forward.
• Develop metrics and tools to analyze errors and understand improvements.
• Collaborate with Perception, Planning, Simulation, and Validation teams to solve autonomous driving challenges.

Skills

Python

Transformer models

Reinforcement Learning

Imitation Learning

Diffusion models

ML pipelines

Education

PhD in CS or related field

Master's degree in CS or related field

Tools

C++

JAX

Job description

Zoox is seeking a Senior / Staff Machine Learning Engineer to develop and deploy behavior models for road users within the simulation stack in Foster City, CA. The role focuses on learning driving agent behaviors using imitation and reinforcement learning, enabling realistic, controllable agents for testing the autonomous driving system.

You will work on large-scale ML pipelines, transformer architectures, and generative models (diffusion/autoregressive) to predict and plan ego-vehicle actions,