Software Engineer, Bulk/Interactive Inference
Core
Building scalable, high-throughput, low-latency inference platforms and data/ML pipelines for Waymo's autonomous driving models and LLMs.
Role type
Senior Staff Software Engineer (ML Infrastructure)
Builds
Waymo's inference platform, model hosting solutions, and ML development pipelines
Domain
Autonomous driving / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
C++, distributed systems, scalable infrastructure design, model inference optimization
Preferred skills
internal tooling development, model hosting experience, exabyte-scale data handling
Technologies
C++, distributed systems frameworks, model inference engines
Responsibilities
Develop scalable inference platform, host internal and external ML models including LLMs, improve inference efficiency, deploy and integrate model inference solutions for distillation, eval, dataset generation, active learning, and auto-labeling
Seniority
Senior Staff, hands-on IC