Data Scientist - Perception Verification and Validation
Summary
Data Scientist on Zoox's Perception Verification and Validation team, defining performance metrics and building/maintaining datasets to quantify the autonomous driving perception stack's performance. Day-to-day work involves large-scale analysis with SQL/Spark and Python, statistical methods to quantify uncertainty, and presenting insights to leadership.
In this role, You will...
- Define key performance metrics that will help perception engineers to measure the impact of new features on the perception stack and the end-to-end system behavior
- Create and maintain datasets used to evaluate the perception stack and end-to-end driving performance.
- Analyze large scale metric results to identify patterns and insights about perception failure modes. Present results and insights to leadership.
- Design and implement statistical methods to quantify uncertainty in our performance and validation metrics.
Qualifications
- Master's or PhD degree in Statistics, Mathematics, Computer Science, or a related field
- Proficient using data query languages (SQL and/or Spark/scala) to quickly build complex yet efficient data queries at scale and using Python to build production-quality code
- Basic experience with autonomous driving, safety-critical systems, or computer vision systems.
- Proficient in exploratory data analysis (EDA) and data visualization to understand and present trends and their implications for the business.
- Background in statistical modeling and analysis; including experience making data-driven decisions that connect point and uncertainty estimates to business impact.
Bonus Qualifications
- Skilled at using AI tools to improve development efficiency and quality.
- Experience with experiment design and statistical comparisons (A/B testing, parametric/non-parametric statistics, etc.)
- Experience analyzing geospatial data
Skills
As published by lever
Resume/CV, Full name, Pronouns, Email, Phone, Current location, Current company, LinkedIn URL, Other website