Staff Software Quality Safety Operations Specialist

Waymo•Mountain View, CA

5h•$190,000 - $234,000

About The Position

The Software Quality Operations (SWQOps) team is at the heart of ensuring the safety, reliability, and quality of the Waymo Driver. Our mission is to build an adaptable and scalable operation, increasingly powered by AI, to deliver the crucial insights necessary to confidently deploy and grow Waymo's autonomous vehicle service. Waymo is undergoing unprecedented growth, rapidly expanding into new cities and launching new vehicle platforms. SWQ Ops plays a critical role in this expansion, making it possible to scale safely and efficiently. The Safety Operations team within SWQ Ops owns the scale delivery of datasets and methodologies used to evaluate the Safety and performance of the driver as Waymo continues to scale. We are on the front lines of de-risking new deployments through meticulous triage of driving and simulated events, issue discovery, and continuous field monitoring, providing early warnings and critical insights. This ensures operational resilience and safety, particularly in new and complex environments. The team also drives engineering velocity by handling performance evaluation, issue deep-dives, and data set curation, allowing Waymo's Engineering, SysEng, Simulation, and Data Science teams to focus on their core tasks. Furthermore, SWQOps enables market expansion by being deeply integrated into every stage of Waymo's market entry framework, providing data analysis, policy development, and quality assurance. The team also supports the development of a single, automated, end-to-end machine learning flywheel for the entire Waymo Driver, which will be the core engine for scaling technology, enabling faster ODD expansion, quicker remediation of driving issues, and a significant reduction in engineering effort.

Requirements

BS/BA degree or 7+ years of relevant work experience in AV Software Quality Operations / ML Operations
Proven ability to manage complex, technical projects and experience working across technical partners (Product, Engineering, Data Science, Systems Engineering) to drive outcomes.
Increased competency in supporting all phases of the machine learning development lifecycle, from data preparation and training to validation, deployment, and continuous monitoring.
Experience with ML testing and validation, including dataset quality assurance, bias detection, edge-case scenario testing, and performance evaluation using statistical metrics.
Ability to quickly learn and implement new concepts and utilize proprietary tools.
Strong understanding of driving rules and regulations.
A proven ability to work in a fast-paced, high-stress environment while maintaining good judgment.
Excellent communication and interpersonal skills to effectively collaborate with a wide range of individuals in a diverse and dynamic work environment.

Nice To Haves

Undergraduate in technical degree preferred.
Experience within A / V space.
Competency in LLM / transformer models, and / or ML for robotics domain experience.
Competency in SQL querying / data analysis.
Experience working with offshore teams / multiple local operations hubs.

Responsibilities

Drive the strategy and technical implementation of decomposing complex safety triage workflows.
Develop and apply advanced operational and ML techniques to enable automation, ensuring scalability as mileage and geographic operations expand.
Serve as the subject matter expert for human-in-the-loop ML systems in the safety problem space.
Define and refine requirements for generating high-quality, dense, and broad human feedback to optimize ML models performance.
Partner with Engineering to design, test, and deploy cutting-edge Machine Learning (ML) and Generative AI (Gen-AI) models and tools to drive step-change improvements in issue discovery & detection, triage efficiency, and quality assurance.
Leverage AI-powered insights and traditional triage signals to proactively identify emerging on-road issue trends, new risk scenarios, and edge cases.
Develop and refine data-driven strategies for issue discovery and monitoring, enhanced by ML model outputs.
Serve as the key link between AI/ML development and operational execution.
Author and drive the adoption of foundational technical policies and standards, strategic roadmaps, and process blueprints that enable the organization to scale and support stakeholder needs.
Advise senior stakeholders on the long-term technical strategy and operational capabilities of the organization, serving as a trusted partner for critical decisions.