Data Engineer/Senior Data Engineer

• Knowing how well our virtual driver drives — and why it fell short — is what lets us ship with confidence
• In this role, you will own that loop end to end: the metrics that quantify driving performance, the pipelines that compute them at fleet scale, the analysis that turns them into judgments about autonomy behavior — including where on the map that behavior changes — the data and tooling that gate software releases, and the agentic workflows that take a detected issue from triage to a proposed fix
• You will work primarily in Python across large-scale data processing, geospatial analytics, evaluation frameworks, and LLM-powered automation
• We welcome engineers from data engineering, analytics, geospatial, evaluation, or robotics backgrounds; prior autonomous-vehicle experience is helpful but not required
• Define and compute driving performance metrics — covering safety, comfort, progress, interventions, and compliance — and build the scalable pipelines that evaluate them consistently across fleet and simulation data
• Analyze road-test and simulation data in depth to identify trends, regressions, and anomalies in autonomy behavior, and turn them into clear findings that engineering teams act on
• Build geospatial analytics over fleet driving data: map-matched metrics, route and corridor performance, location-based clustering of events and issues, and geographic coverage analysis that shows where the virtual driver performs well and where it struggles
• Build the data foundations and tooling for release management, including release-over-release comparisons, readiness and gating criteria, and traceable evidence supporting release decisions
• Build AI agentic workflows that triage detected issues at scale — clustering and deduplicating failures, attributing root cause, routing to the right owners, and proposing fixes with supporting evidence for engineering review
• Ensure that your work is performed in accordance with the company’s Quality Management System (QMS) requirements and contribute to continuous improvement efforts

Benefits

• Unlimited PTO: Unlimited paid time off on top of company holidays to recharge and enjoy as needed
• Flexible working: Flexibile work arrangements and technology to help manage life’s demands at the office and remote
• Health benefits: Tiered options in medical, dental, and vision insurance to fit your unique needs
• Future building: Equity, 401k and FSA options for all eligible employees to help build for your future
• Professional development: Company-sponsored professional development opportunities such as conferences, training, and workshops
• Catered lunches: Daily catered lunches at both of our Santa Clara and Fremont offices

• You do not need experience with every technology in our stack; we value strong fundamentals, ownership, and the ability to learn
• We are open to candidates at either the Engineer or Software Engineer level. Level will be determined by experience, technical depth, scope of ownership, and demonstrated impact
• Experience building LLM-powered or agentic workflows for data analysis, evaluation, or automation
• Proficiency in Python, with experience building scalable data processing systems or evaluation frameworks
• Self-driven with a strong sense of ownership: a quick learner who is eager to take responsibility and drive projects forward end to end
• Experience developing metrics and analyzing large-scale time-series, event, or geospatial data, including principled metric definitions, validation, and error analysis
• BS, MS, or PhD in Computer Science, engineering, or a related technical field, or equivalent practical experience
• Ability to solve open-ended technical challenges and communicate findings clearly to engineering and program stakeholders
• Experience with distributed data processing such as Apache Spark, and workflow orchestration such as Airflow or Argo Workflows
• Experience with geospatial data and tooling, such as GIS formats, map matching, spatial indexing and joins, PostGIS, GeoPandas, or map-based visualization libraries
• Familiarity with LLM agent frameworks (e.g., LangChain, LangGraph, or similar) and prompt/tool-orchestration patterns
• Experience with release engineering, quality gating, or automated regression detection
• Experience with autonomous vehicles, robotics, or other safety-critical systems
• Experience building dashboards or analytics interfaces that expose metrics to users