Quick overview
Job description
Zoox is building advanced self-driving hardware and software solutions. To attain the utmost efficiency that the system demands, we need you - an expert who understands both compute hardware architecture as well as the algorithms and middleware that run on it. Your contributions will be instrumental in finding & detecting performance-related trends and anomalies across the robot fleet.
The Software Performance team’s mission is to analyze, optimize and provide guidance to the software and hardware teams in order to meet expected system performance & stability targets.
As an automation engineer within the Software Performance team, you will build automated instrumentation, benchmarking and analysis for compute performance (CPU, GPU, latency and memory) into the software development and release process. Your work will catch performance regressions before software reaches the fleet, identify trends and anomalies across releases and hardware platforms, and put detailed performance data at the fingertips of performance experts for quick and efficient investigations.
In this role, you will:
-
Automate common workflows & processes for performance data storage and analysis (CPU, GPU, latency, memory, etc)
-
Build agentic harness to support efficient triage & investigations of performance issues, iterative loops for self-optimizations.
-
Make dense performance metrics accessible to the software organization for use in release monitoring/gating as well as agent driven optimization loops.
-
Work cross-functionally to ensure performance tooling is integrated with Zoox continuous integration and release management processes, and support releases by triaging latency and memory regressions with application teams.
Qualifications:
-
3+ years of professional experience in software development or related fields and BS in computer science or related field
-
Strong knowledge of Python, proficiency in C++, and experience in large code bases
-
Expertise in continuous integration systems (Buildkite, GitHub Actions, Jenkins, or similar)
-
Experience using LLMs and agentic AI to automate engineering workflows
-
Good communication and organizational skills, with a logical approach to problem-solving, good time management, and task prioritization skills
Bonus Qualifications
-
Proficiency with Git and Bazel
-
Experience with software and hardware benchmarking and Hardware-in-the-Loop (HIL) systems
-
Savvy with efficient SQL queries and data platforms such as Databricks, Looker, and ETL pipelines
Haystack's AI agent can fill in and submit this application for you. How AI auto apply works
