Data, machine learning, and statistical models help build the Waymo Driver and in evaluating its performance. Waymo data scientists work with engineering to confirm reasoning and validation about data and models in our production systems. We develop metrics and experimental designs that capture performance aspects of our autonomous systems. Examples of areas the data science team is involved in include safety readiness evaluation, development of signals to characterize good driving, evaluation of ML models in production systems, and simulation technology (virtual driving).

In this hybrid role, you will report to the Manager of Data Science.

You will:

• Develop evaluation frameworks for both autonomous vehicle performance and the evaluation frameworks themselves ("eval of eval").
• Develop statistical methods and ML models to analyze historical/simulation data.
• Frame and solve ambiguous problems and communicate the results.
• Develop new metrics, interpret trends, and investigate anomalies in data from simulation and our rider-only service
• Mentor other data scientists, either formally (as a tech lead) or less formally (as an individual contributor).

You have:

• PhD in a quantitative field (e.g. Statistics, Mathematics, Physics)
• 3+ years of industry experience solving large-scale problems
• Expertise using advanced statistical methods (e.g., ML models, hypothesis testing, causal analysis)
• Demonstrated knowledge of Python/SQL/R data analysis libraries and packages

We prefer:

• Experience solving problems related to Autonomous Driving
• Experience in adjacent relevant areas like Advanced Machine Learning (Deep Learning and Diffusion models), Traffic Modeling, Safety Evaluation or Prediction
• People leadership experience

#LI-Hybrid