Contract Student Worker, Zoox

• Assist analyzing large-scale driving and simulation datasets to identify trends, edge cases, and opportunities to improve autonomy performance
• Currently pursuing a B.S. or M.S. in a relevant quantitative field (Engineering, Computer Science, Statistics, Physics, or similar)
• Strong programming skills in Python
• Help work through ambiguous, open-ended problems with a researcher’s mindset and a bias toward rapid iteration
• Solid data manipulation understanding (e.g., SQL, PySpark, Scala)
• Solid foundation in statistics, machine learning, and risk or reliability modeling
• Help communicate complex results, trade-offs, and uncertainty clearly to the team and stakeholders
• Comfort operating independently under high uncertainty on open-ended problems
• ---Program Requirements---
• Genuine interest in autonomous vehicles and Zoox’s mission
• Currently enrolled in a B.S. or M.S. program in a relevant discipline
• Available to commit to a minimum three-month assignment
• Able to commit a minimum of 20 hours per week
• Able to work on-site at one of our office locations
• Must adhere with Zoox confidentiality requirements, including refraining from using or sharing proprietary company information outside of Zoox, such as in academic research, theses, publications, or presentations

Desirable

• This role focuses on building a data-driven safety risk model that quantifies and improves autonomous-vehicle driving performance, along with the data analysis work that supports it
• The student will work within the Safety Strategy & Operations team on a 6-month project spanning model development, empirical experimentation, and large-scale driving/simulation data analysis
• Support designing, building, and iterating on a data-driven safety risk model that quantifies driving performance and surfaces safety-relevant signals across the autonomy stack
• Assist developing and maintaining dataset management pipelines — curation, labeling, versioning, and quality checks — that feed the risk model and downstream analyses
• Support defining and running empirical experiments that “show it with data” rather than relying on assumptions