Senior Software Engineer - Autonomy Safety Metric
- Foster City, CA
- Hybrid
- Senior level
- 7+ yrs experience
- Data Platform / Data Engineering for Autonomy Safety Evaluation
- Visa: not specified
- $239k–$280k
The role in 30 seconds
This role sits on the Behavior Evaluation team at Zoox, which quantifies how often the autonomous driving stack causes unexpected stops and maps that to collision risk. The engineer owns and scales the data pipelines and statistical methodology behind weekly per-geofence safety estimates, making the system faster, more reliable, and easier to audit as Zoox expands to new cities and releases.
Is this role a fit for you?
The backgrounds this role is most likely to hire from, as RoleStack reads the posting.
Strong match
- Data platform / ML pipeline
- B2B infrastructure / API / developer tools
- Enterprise-scale
- Growth-stage
Workable stretch
- B2B enterprise platform / workflow software
- Startup / greenfield
Harder transition
- B2C consumer-facing application
- Embedded systems / hardware-adjacent
- Regulated environment
Industry: Automotive & Transportation (autonomous driving). See your personal match score
What they're really screening for
Must-haves
- CORE 7-9 years of experience, or 5+ years with a strong data-platform track record
- CORE Expert Python, with production experience in PySpark/Spark and Pandas
- CORE Experience designing scalable batch data pipelines: orchestration, Delta/lakehouse tables, idempotent backfills
- CORE Solid grounding in applied statistics: sampling, weighting, estimators, confidence intervals
- PLUS Strong testing and CI habits for data code
- CORE Experience with autonomous-vehicle simulation, safety metrics or triage workflows
- PLUS Experience putting ML models into production in a data pipeline
- PLUS Experience with Databricks and AWS (EMR Serverless, S3)
- PLUS Experience building for autonomous-driving/AV safety evaluation users or similar safety-critical measurement stakeholders
Résumé keywords for this role
Terms the posting stresses. Include the ones you can honestly back up.
Tools & technologies
- PySpark
- zspark
- Databricks
- EMR Serverless
- Airflow
- Python
- Spark
- Pandas
- Delta
- lakehouse
- AWS
- S3
- CI
- ML models
Concepts & phrases
- Behavior Evaluation
- autonomy safety metric
- autonomous driving technology
- per-geofence estimates
- medallion architecture
- batch data pipelines
- idempotent backfills
- applied statistics
- confidence intervals
- safety metrics
- triage workflows
- ML model scoring
- data-platform track record
- cross functional stakeholders
- release methodologies
Words that count as the same thing: "PySpark/zspark" ≈ PySpark, Spark, Apache Spark · "medallion architecture" ≈ lakehouse medallion architecture, bronze/silver/gold data layers · "Delta/lakehouse tables" ≈ Delta Lake, lakehouse tables, Databricks Delta · "EMR Serverless" ≈ AWS EMR, EMR · "autonomy stack" ≈ autonomous driving stack, AV stack
Check my résumé against these keywordsHiring at Zoox
All Zoox hiring dataOpen senior roles RoleStack tracks right now, posted in the last 30 days.
More open roles at Zoox
- Senior Technical Program Manager - Guidance & Routing $202k–$236k
- Senior/Staff Technical Product Manager, Agentic AI Transformation $212k–$267k
- Senior/Staff Software Engineer, Core Connectivity $255k–$320k
- Senior/Staff Technical Program Manager - Automation & Scaling $213k–$295k
- Senior/Staff Technical Program Manager - Process and Tools $193k–$279k
Full job description from Zoox
From Zoox's posting. View the original
We are seeking a highly skilled and experienced engineer to join the Behavior Evaluation team and play a pivotal role in measuring the safety of Zoox’s autonomous driving technology. The Behavior Evaluation is the team behind the behavioral part of Zoox’s estimate, quantifying how often the autonomy stack causes the vehicle to stop unexpectedly and how that maps to collision risk. As a member of this team, you will own and scale the pipeline behind these numbers, driving innovation in ML model scoring, sampling, and projections while making the system faster, more reliable, and easier to audit. You will work closely with a team of talented engineers and researchers in a fast paced, collaborative environment as Zoox expands to more cities and software releases.
Show full description Show less
• 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.
• 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
• Experience with autonomous-vehicle simulation, safety metrics or triage workflows
• Experience putting ML models into production in a data pipeline
• Experience with Databricks and AWS (EMR Serverless, S3)
FAQ
How much does a Senior Software Engineer - Autonomy Safety Metric at Zoox make?
The posted pay for this role is $239k–$280k a year.
How much experience do you need?
The posting asks for 7+ years in data platform / data engineering. It is a senior-level role.
Does Zoox sponsor visas for this role?
The posting does not say whether visa sponsorship is available. Ask the recruiter before you apply.
Is this role remote?
It is a hybrid role: part remote, part in the office.
What tools and technologies does the posting mention?
PySpark, zspark, Databricks, EMR Serverless, Airflow, Python, Spark, Pandas, Delta, lakehouse, AWS, S3, CI, ML models.