| Location | Sunnyvale, CA |
| Salary | $40–$50 Per Hour |
We are building a high-velocity team of multi-disciplinary experts to turn real-world operations into high-quality data for our autonomous partners. Autonomy is now a data race, and we collect rare, real-world driving data at a scale and capital efficiency no one else can match.
As an AV Quality Assurance Specialist, you will serve as a crucial technical bridge between real-world fleet operations, system validation engineering, and data pipeline teams. You will perform first-level analysis on complex fleet driving logs, execute initial root-cause triage on system disengagements, enrich raw driving data with structured metadata, and validate automated triage tooling. This role requires a meticulous, safety-first mindset and a passion for data-driven debugging to maintain the high fidelity of our autonomous dataset.
Data Triage & Log Analysis: Perform first-pass investigation of real-world run data, system overrides, and edge-case disengagements using specialized log visualization tools.
Metadata & Issue Tagging: Enrich intervention events with precise root-cause labels, Jira issue links, contextual tags, and diagnostic notes to accelerate dataset curation.
Issue Lifecycle Management: Support end-to-end issue tracking across identification, initial investigation, cross-functional routing, and documentation.
Tooling Feedback & QA: Test and validate automated triage scripts, bots, and internal diagnostic dashboards, delivering actionable feedback to improve tooling throughput.
Cross-Functional Collaboration: Partner closely with AV System Validation Engineers, Software Pods, and Field Operations to maintain standardized triage SOPs.
First-Pass Data Analysis: Perform structured first-pass analysis on incoming real-world fleet data, system overrides, and driver interventions to identify anomalous software or hardware behavior.
Root-Cause Classification & Metadata Enrichment: Accurately apply standardized root-cause labels, metadata tags, and bug tracking links to disengagement events, ensuring high dataset fidelity for downstream model training and scenario simulation.
Collaborative Issue Lifecycle Tracking: Track and manage issues through their full lifecycle—from initial field recording to engineering handoff and resolution verification.
Automation Bot & Tooling Validation: Actively test, validate, and evaluate triage automation scripts and internal visualization dashboards, providing feedback to developer teams to eliminate workflow bottlenecks.
Operational SOP Execution: Follow and iterate upon operational playbooks and Standard Operating Procedures to ensure consistent, bias-free, and high-accuracy triage outcomes across distributed shifts.
Trend Identification: Assist System Validation Engineers in spotting recurring edge-case patterns, hardware dropout trends, or dataset annotation anomalies.
Experience: Minimum 1–2+ years of technical operations, quality assurance, data triage, or software/hardware testing experience in autonomous vehicles, ADAS, robotics, aerospace, or safety-critical industries.
Data & Log Triage Skills: Demonstrated ability to perform log analysis, troubleshoot complex technical workflows, and navigate issue-tracking ecosystems (e.g., Jira, Confluence).
Scripting & Data Basics: Basic proficiency with scripting languages (e.g., Python, Bash) or database queries (SQL) for log parsing, metric verification, or data filtering.
Technical Terminology: Strong familiarity with autonomous vehicle terminology, software release workflows, and multi-sensor hardware systems.
Education: Bachelor's degree in Engineering, Computer Science, Data Analytics, Information Systems, or equivalent technical practical experience (desired but not required).
Domain Expertise: Experience with multi-modal sensor suites (Lidar, Radar, Cameras) and familiarity with CAN bus diagnostic logging tools or time-series data visualization platforms.
Validation & Simulation Exposure: Prior exposure to virtual simulation platforms (Software-in-the-Loop) or physical test bench environments (Hardware-in-the-Loop).
Quality & Safety Mindset: Proven track record of high detail orientation, bias-free problem-solving, and strict adherence to technical safety playbooks.