Zoox is transforming mobility-as-a-service by developing a fully autonomous, purpose-built fleet designed for AI to drive and humans to enjoy.
Reliability is foundational to scaling an autonomous mobility service. As the Prognostics Technical Lead, you will define and lead Zoox’s technical approach for predicting failures before they occur, enabling smarter maintenance, reducing unplanned downtime, and improving fleet availability.
In this role, you will sit at the intersection of field reliability, data, diagnostics, vehicle engineering, and service operations. You will lead the development of prognostics strategies for critical vehicle systems, translate real-world failure behavior into deployable health monitoring approaches, and help the organization decide where prognostics is the right lever versus diagnostics, preventive maintenance, or design change.
You will be expected to operate as both a technical leader and systems thinker: shaping the roadmap, guiding model and monitor development, aligning cross-functional partners, and ensuring prognostics work is grounded in actual fleet impact. This role is ideal for someone who can move fluidly between failure physics, field data, estimation methods, algorithm development, and operational implementation.
In this role, you will:
Lead Zoox’s technical strategy for prognostics across vehicle systems, with a focus on reducing in-service failures and improving fleet availability
Identify and prioritize the failure modes where prognostics can create meaningful operational value, based on failure behavior, detectability, warning horizon, and serviceability
Develop and manage prognostics concepts, methodologies, and technical requirements for monitoring degradation, predicting remaining useful life, and detecting pre-failure behavior in fielded systems
Partner with reliability, design engineering, service, firmware/software, and data teams to define the signals, features, infrastructure, and product changes needed to enable effective prognostics
Work with Design Reliability and Field Reliability to translate field performance, repair history, usage patterns, and failure analysis into monitor strategies and deployable health indicators
Guide the development, validation, and tuning of prognostic models and health monitoring algorithms using field and test data
Establish technical frameworks for evaluating prognostic performance, including sensitivity, false positive burden, lead time, robustness, and operational usefulness
Drive tradeoff decisions between prognostics, diagnostics, inspection intervals, and design improvement based on risk, cost, and implementation practicality
Help build the data and analysis architecture needed to support prognostics at scale, including data quality requirements, feature generation, monitor traceability, and performance feedback loops
Partner with service operations to ensure prognostics outputs translate into actionable maintenance decisions, clear workflows, and measurable business value
Provide technical leadership and mentorship across the prognostics workstream, raising the bar on methods, rigor, and cross-functional execution
Communicate recommendations, risks, and roadmap priorities clearly to engineering leadership and cross-functional stakeholders
Qualifications
Bachelor’s, Master’s, or PhD in Mechanical Engineering, Electrical Engineering, Aerospace Engineering, Systems Engineering, Statistics, Applied Mathematics, Computer Science, or a related field
8+ years of experience in prognostics, health monitoring, reliability engineering, condition-based maintenance, or closely related domains
Strong understanding of failure modes, degradation behavior, reliability fundamentals, and the practical challenges of predicting failure in complex systems
Experience developing or deploying prognostic, anomaly detection, or health monitoring methods for real-world hardware systems
Experience working with field data, sensor data, maintenance data, and failure analysis to drive engineering decisions
Strong quantitative and analytical skills, including experience with statistical modeling, degradation analysis, or machine learning approaches relevant to health monitoring
Proficiency in Python or similar technical computing tools for analysis, prototyping, and model development
Demonstrated ability to lead technically across functions and influence teams without direct authority
Strong written and verbal communication skills, with the ability to explain complex technical topics in an actionable way
Bonus Qualifications
Experience in automotive, EV, robotics, aerospace, industrial equipment, or other safety- and uptime-critical systems
Experience working with vehicle telemetry, embedded sensing, CAN or log data, diagnostics, or onboard/offboard health monitoring architectures
Experience building or guiding production-grade analytical workflows, model pipelines, or monitoring systems
Experience with remaining useful life estimation, fault detection and isolation, or condition-based maintenance frameworks
Experience evaluating model performance in production environments, including false alert burden, monitoring drift, and field feedback loops
Familiarity with service operations, maintenance workflows, and the real-world constraints of deploying predictive maintenance systems
Experience operating in fast-moving product environments where reliability, software, hardware, and operations must work together closely
Familiarity with cloud-based data platforms and the practical challenges of deploying models beyond offline analysis
Experience applying physics-informed, statistical, or machine learning approaches to degradation modeling and health monitoring
Experience partnering closely with service or maintenance organizations to operationalize predictive maintenance workflows
Strong intuition for when prognostics is the right solution versus when diagnostics, preventive maintenance, or design change is more effective
