Senior Autonomy Safety Metrics Engineer

Zoox; Foster City (CA); On-site; USD 239,000 - 280,000; Full time

Benefits offered by this job

Health insurance

RSUs

Stock Appreciation Rights

Paid time off

Sign-on bonus may be offered

Job summary

Zoox is seeking an experienced engineer for the Behavior Evaluation team to scale data pipelines that quantify safety metrics for the autonomous driving stack. You will own end-to-end data processing, from sampling and weighting to weekly geofence estimates, with a focus on reliability and auditability.

The role emphasizes production Python, PySpark/Spark, Pandas, and designing scalable batch pipelines integrated with Databricks and AWS. Strong CI and testing practices are essential.

Qualifications

• 7–9 years of experience or 5+ years with a strong data-platform track record.
• Expert Python, with production experience in PySpark/Spark and Pandas.
• Experience designing scalable batch data pipelines: orchestration, Delta/lakehouse tables, idempotent backfills
• Solid grounding in applied statistics: sampling, weighting, estimators, confidence intervals
• Strong testing and CI habits for data code

Responsibilities

• Build and maintain the Behavior Evaluation data pipelines (PySpark/zspark medallion architecture on Databricks, EMR Serverless and Airflow) that produce weekly per-geofence estimates.
• Turn the statistical method (sampling, triage weights, mileage sharing, projections) into tested, reproducible code with checks that fail loudly when the data is bad.
• Build tools that cut the manual work in each weekly run.
• Work with cross functional stakeholders so the methodology is applied consistently in code and in clearance reports.
• Help adapt to new release methodologies and new geofences.

Skills

Python

PySpark

Pandas

Statistics

CI/CD

Tools

Databricks

AWS

Airflow

Spark

Job description

Zoox is seeking an experienced engineer for the Behavior Evaluation team to scale data pipelines that quantify safety metrics for the autonomous driving stack. You will own end-to-end data processing, from sampling and weighting to weekly geofence estimates, with a focus on reliability and auditability.

The role emphasizes production Python, PySpark/Spark, Pandas, and designing scalable batch pipelines integrated with Databricks and AWS. Strong CI and testing practices are essential.