Director, Simulation Evaluation

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. We are using state of the art machine learning in our evaluation to ensure we can scale to meet Waymo's goals. We collaborate across teams to bring insights and applicable metrics to teams working on the onboard software and the rider experience. 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.

You will report to our Simulation and Evaluation Director in a hybrid role.

You will:

• Lead the development of evaluation methodologies for Foundation Models and production models: Research and propose new ways to assess the quality, safety, and realism of ML models used to create driving plans, agent trajectories and other core inputs to driving. This includes exploring new metrics, statistical analysis, and validation techniques applicable to both Waymo Research's modern Foundation Models and the production models deployed in the Waymo Driver.

• Be an expert in Waymo's AI efforts, focused on measurement.

• Lead and contribute directly to the design of ML evaluation tools: Develop, and improve evaluation tools that allow model hillclimbing and inform production model release decisions. You will collaborate with engineers to define requirements, designing new features, and providing support for these tools, ensuring they meet the needs of both research and production environments.

• Partner with teams in Planner and Research to launch new and improved ML evaluation products that directly address our requirements, ensuring that evaluations are aligned with the goals of the Waymo Driver and our goals.

• Use Waymo's industry-leading datasets and evaluation frameworks: Establish evaluation frameworks to conduct reliable evaluations, ensuring that model improvements translate into measurable gains in fleet-wide performance.

• Employ creative simulation strategies to measure the driving performance of generative AI models: Identify potential edge cases, and provide reliable performance insights that inform model development and deployment. Build data pipelines for signal discovery, data labeling, feature extraction and metric computation based on large-scale simulations.

• Manage an experienced team of SWE, DS and ML experts.

You have:

• Masters in a quantitative field such as ML, stats, math, physics or robotics

• 10+ years of experience solving challenging technical problems in a production context

• Experience defining and implementing evaluation strategies

• Mastery of data-driven report writing and technical strategy documentation for executive decision-making

• Technical leadership experience including prior hands-on involvement with the development of large-scale AI, LLM or AV systems
  
  

We prefer:

• PhD in a quantitative field such as ML, stats, math, physics or robotics

• Experience with modern AI in the context of self driving.

• Mentorship and leadership development experience

• Experience leading technical teams

#LI-Hybrid