About this role
Engineers who thrive in complex adversarial domains and enjoy safeguarding critical infrastructure against sophisticated threats will find a strong fit in this position. Waymo operates an autonomous driving technology organization focused on scaling the Waymo Driver across multiple mobility platforms and markets.
This engineering team builds and maintains the machine learning systems and low-latency pipelines that prevent payment fraud, mitigate financial risk, and protect vehicles from vandalism during active trip creation. Team members collaborate closely with Product, Finance, and Safety departments to deploy real-time model serving infrastructure while balancing strict latency budgets and regulatory compliance.
The role exists to ensure revenue protection and operational security as the company expands its autonomous ride-hail services globally. Successful candidates typically bring a solid background in distributed backend development, practical machine learning deployment, and a methodical approach to handling rapidly evolving security challenges.
What you will do
- Train, evaluate, and ship production machine learning models that score rider risk in real time to protect payment revenue and reduce vehicle vandalism.
- Engineer and maintain high-throughput, low-latency feature pipelines across payment, trip, device, and identity events.
- Ensure data consistency between offline training environments and online serving systems.
- Build and operate real-time model serving infrastructure integrated into critical trip creation and payment authorization paths under strict latency and availability budgets.
- Design and implement safe, graduated enforcement mechanisms that feature full audit trails, reversibility, and rider appeal support.
- Partner cross-functionally with Product, Finance, and Safety to balance revenue protection, rider trust, and compliance during market expansion.
What you need
- Hold a Bachelor's degree in Computer Science, Mathematics, Statistics, or possess equivalent practical experience.
- Bring 5 or more years of software engineering experience building distributed backend systems or production machine learning systems using languages such as Python, Java, Kotlin, C++, or Go.
- Demonstrate hands-on experience in training, evaluating, and deploying machine learning models to production.
- Possess practical experience serving models or critical business logic within low-latency, high-availability production environments.
- Demonstrate strong fundamentals in data modeling and SQL analytics.
Nice to have
- Experience in fraud prevention, risk management, trust and safety, payments, or other adversarial domains with actively adapting attackers.
- Experience with graph or entity-clustering techniques, rules engines, and anomaly detection alongside traditional machine learning.
- Proven track record of building feature and data pipelines while maintaining consistency between training data and real-time inference.
Skills and tech stack
Questions candidates ask
What team will I be working with in this role?
You will partner cross-functionally with Product, Finance, and Safety teams to balance revenue protection, rider trust, and compliance as the company scales to new markets.
What kind of systems and infrastructure will I build?
You will engineer high-throughput, low-latency feature pipelines over payment, trip, device, and identity events, and build real-time model serving infrastructure integrated into critical trip creation and payment authorization paths.
What is the primary focus of the machine learning models?
You will train, evaluate, and ship production machine learning models to score rider risk in real time, directly protecting revenue from payment fraud and reducing vehicle vandalism.