The opportunity
Waymo is an autonomous driving technology company with the mission to be the world's most trusted driver. Since its start as the Google Self-Driving Car Project in 2009, Waymo has focused on building the Waymo Driver—The World's Most Experienced Driver™—to improve access to…
What you'll do
Eval pipeline optimization (orchestration level): Finding opportunities to decrease e2e execution cost by reducing overhead or increasing parallelism in jobs
Eval pipeline optimization (model level): Improving eval workload efficiency by improving exported model efficiency in CPU or TPU export configurations
Pipeline observability: Providing insights and high level metrics on pipeline runtime and success rate
LLM integration: Finding better ways to integrate agents with eval workflows. This could be making it easier for agents to run evals accountably, or making it easier for agents to contribute maintainable code to the eval codebase
Reading/writing pipeline and implementation code
Profiling and understanding slowness within distributed systems
What they're looking for
- Building custom harnesses to isolate components of the system
- Querying existing logs and data sources for aggregate statistics
- Currently pursuing a Bachelor’s degree in software engineering or a related field
- Working knowledge of Python
