Waymo is looking to build and maintain critical data and ML pipelines to power ML development and improve the efficiency of autonomous driving technology.
Requirements
- 2+ years of professional experience in the field of software engineering
- Experience in programming C++
- Experience with building highly scalable distributed system
- Passionate about building internal infra and tools
- Experience with building model hosting and inference solutions
- Experience with handling datasets in the order of exabytes
Responsibilities
- Develop Waymo's inference platform to make it scalable, high throughput, and low latency
- Work closely with other teams across Waymo in hosting both internal and external ML models, including LLMs
- Improving the efficiency of running inference on these large models to increase throughput and save cost
- Deploy and integrate model inference solutions across a variety of use cases, such as distillation, eval, dataset generation, active learning, and auto-labeling
Other
- In this hybrid role, you will report to the Head of ML Platform- Senior Staff Software Engineer
