The Driver Understanding and Evaluation team at Waymo develops a rich understanding of Waymo Driver's behavior. With over 1 million driverless miles per week, it is critical that Waymo can understand and assess the behavior of all its vehicles - both in the field and in simulation - with automated algorithms. The learned metrics team is a strategic bet to use machine learning to ensure we can scale to meet Waymo's goals. We collaborate across teams to bring ML to production systems and build what is Waymo's reward function. We build and operate large-scale machine learning and data systems, simulation workflows, and insight tools. We combine expert human judgements and advanced machine learning models to deliver training and evaluation data for the Waymo driver. We are looking for researchers and software engineers who are passionate about developing production grade machine learning systems for our autonomous vehicles and have an incessant drive to improve the performance of our technology stack.

In this role, you will:

• Report into the TLM for the Learned Metrics Team
• Develop and improve ML models that assess our autonomous vehicle's behavior.
• Develop ML infrastructure to support robust and performant models.
• Collaborate across teams to bring state-of-the-art to production.

You have:

• PhD in Computer Science, Robotics, Statistics, Physics, Math or another quantitative area, or equivalent work experience
• 2+ years of experience building productionized ML models
• Strong coding and design skills: comfort building production systems (Python / C++)
• Strong background and experience in applied Deep Learning
• A strong track record in improving model quality

We prefer:

• 4+ years of experience building productionized ML models
• Experience in reinforcement learning, transfer learning, and/or multi-task learning.
• Experience with large scale data and models

#Li-Hybrid