Develop models and analyses to optimize system performance across competing constraints (e.g., power usage vs data quality vs responsiveness)
Define and implement end-to-end observability, establishing metrics across system components and dependencies
Design and run experiments (e.g., pre/post, control vs test) to evaluate changes and detect regressions at both component and system levels
Build and refine anomaly detection and failure analysis methods across complex, real-world data
Lead ad hoc investigations into system issues, identifying root causes and driving resolution with cross-functional teams
Translate insights into actionable recommendations across Firmware, Hardware, Software, and Operations, driving measurable improvements in system behavior
Develop predictive systems for early issue detection and performance forecasting, including in environments with limited historical data
Continuously evolve analyses into scalable intelligence systems that support monitoring, decision-making, and automation

5+ years of experience in data science working on production systems or real-world applications
Proven experience building, deploying, and maintaining models in production environments
Strong proficiency in Python and SQL
Experience working with complex, real-world datasets (e.g., time-series, event-based, or system-generated data)
Strong foundation in statistical analysis, experimentation, and/or anomaly detection
Proven ability to bring structure to ambiguous, open-ended problems, iterating quickly to drive toward practical, high-impact solutions (80/20 mindset)
Experience working cross-functionally with engineering and operational teams

Health, Dental & Vision (Gold and Platinum with some providers plans fully covered)
Paid parental leave
Alternating day off (every other Monday)
“Off the Grid”, a two week per year paid break for all employees.
Commuter allowance
Company-paid training

Senior Data Scientist, Fleet Performance Optimization

Key skills