Waymo is looking to build and evolve ML inference infrastructure for simulations to improve the reliability, latency, and user experience of ML model deployment and serving.
Requirements
3+ years of experience C++ and/or Golang programming experience
Experience in developing and maintaining distributed systems.
Experience working with large-scale distributed inference service.
Experience working with popular ML frameworks, TPUs and optimizing models for serving.
Experience with distributed systems principles, including scheduling, load balancing, and fault tolerance.
Experience working with large FAANG scale distributed systems.
Responsibilities
Build and evolve ML inference infrastructure for simulations.
Be responsible for the reliability, latency, and user experience of ML model deployment and serving.
Other
In this hybrid role you will report to the Software Engineering Manager.
B.Sc. in Computer Science, or a related field, or equivalent years of experience
