Zoox직원 1000-5000명
Software Engineer - Collision Avoidance System Metrics
Foster City, CA · 2026년 11월 15일 처음 확인
- 급여
- 급여 미공개
- 위치
- Foster City, CA
- 직급
- 명시되지 않음
- 게시일
- 2026년 11월 15일
- 출처에서 날짜를 공개하지 않았습니다
직무 소개
The Collision Avoidance System (CAS) is responsible for detecting and reacting to imminent collision situations in support of our vehicle’s overall safety goals. CAS Perception is responsible for processing raw sensor data from our vehicle’s world-class sensor suite using a combination of geometric, interpretable algorithms and deep learning to detect near-collisions with obstacles along our intended driving path, in the most challenging dense urban environments and under tight compute resource constraints. Overall CAS is parallel and complementary to our Main Artificial Intelligence (AI) autonomy stack, and has a close relationship with our vehicle hardware and safety teams in order to architect redundancy into our overall driving system.
The CAS Verification & Validation (CAS V&V) is a multidisciplinary team data, software and systems engineers defining and building metrics to measure the Collision Avoidance System performance and work with the Systems Design and Mission Assurance (SDMA) and QA teams to develop validation plans for the features.
In this role, you will:
• Apply distributed computing algorithms to analyze petabytes of urban driving data.
• Develop metrics and tools to analyze errors and system improvements.
• Work closely with CAS engineers to evaluate system performance.
• Collaborate with Perception engineers to define metrics for autonomous driving.
• Partner with Planning engineers to measure performance in complex urban environments.
Qualifications:
• BS, MS, or PhD degree in computer science or a related field
• Fluency in C++ and/or Python
• Extensive experience with programming and algorithm design
Bonus Qualifications:
• Experience with analysis of latency for safety-critical software systems
• Experience with petabyte-scale distributed computing (Spark, Databricks, generic MapReduce pipelines)
• Background in Bayesian statistics