Simulation Expert Triage Engineer

Zoox; Foster City (CA); On-site; USD 100,000 - 130,000; Full time

Job summary

Zoox is seeking an experienced system triage engineer in Foster City, California, to enhance AI performance assessments through effective triage processes. Your key responsibilities will include coordinating triage efforts, categorizing issues based on severity, and recommending process improvements.

Applicants should have over 5 years of experience in systems troubleshooting, ideally related to autonomous driving, along with strong capabilities in root cause analysis and familiarity with Agile methodologies.

Qualifications

• 5+ years of experience in systems troubleshooting and diagnostics.
• Experience in a Quality Assurance or Triage role for Autonomous Driving.
• Experience with root cause analysis of an autonomous vehicle stack.

Responsibilities

• Run the triage process on a regular basis.
• Perform expert triage on events daily.
• Categorize and prioritize issues based on severity, urgency, and potential impact.
• Identify trends in system failures aligned with AI metrics.
• Develop and maintain objective triage processes.

Skills

Systems troubleshooting and diagnostics

Quality Assurance or Triage experience

Git

Agile methodologies

Scripting/programming languages (Python)

Root cause analysis

Job description

Our group’s mission is to design, prototype, and produce novel methods and tools for efficient modeling and simulations of complex systems at scale. These tools aid in measuring the safety of our AI and readiness for launch. We use recent advances in machine learning, statistics, optimization, and numerical methods to verify and validate our software and AI in the most challenging environments and subsequently develop tools to enable other teams at Zoox to do the same.

We are looking for an experienced system triage engineer who can evaluate and synthesize AI‑driving performance in large‑scale simulation sets. In this role, you will be responsible for running the weekly triage process. This entails coordinating the team members involved in the steps of the triage process, providing expert triage of simulation results, reviewing the quality of triage results, and distilling results for communication with AI developers and executives. You will work cross‑functionally with engineers in AI, simulation, infrastructure, and data science to provide reliable and trusted measures of AI performance. You will recommend improvements that can be made to the triage process in terms of tooling or automation. You will document issues in the driving software, simulator or scenario definitions and work with the appropriate teams to get these issues resolved.

Responsibilities

• Run the triage process on a regular basis
• Perform expert triage on events daily
• Effectively categorize and prioritize issues based on severity, urgency, and potential impact on safety and performance
• Identify trends in system failures and work cross‑functionally to align AI performance metrics
• Develop and maintain objective triage processes
• Recommend improvements to the triage process and tools (including AI tools and automation)

Qualifications

• 5+ years of experience in systems troubleshooting and diagnostics, preferably in the automotive or other industry where safety is critical
• Experience in a Quality Assurance or Triage role for Autonomous Driving
• Experience with Git, Agile methodologies, and scripting/programming languages (preferably Python)
• Experience with root causes analysis of an autonomous vehicle stack