Staff Machine Learning Engineer, Tech Lead Active Learning
About The Position
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 mobility while saving thousands of lives now lost to traffic crashes. The Waymo Driver powers Waymo’s fully autonomous ride-hail service and can also be applied to a range of vehicle platforms and product use cases. The Waymo Driver has provided over ten million rider-only trips, enabled by its experience autonomously driving over 100 million miles on public roads and tens of billions in simulation across 15+ U.S. states. The Active Learning team builds tools and infra that empower all ML Engineers at Waymo to manage their ML datasets to efficiently train high quality models. These systems include solutions for data mining, data labeling, data understanding, model evaluation, model inference, model calibration, and dataset management. We are looking for a Technical Lead to join our team to apply the latest techniques in training / evaluation dataset management. In this hybrid role, you will report to a Technical lead Manager, Staff Software Engineer.
Requirements
- 8+ years of professional experience in the field of software engineering
- Experience programming in C++ or Python
- Experience building scalable, effective data pipelines including data materialization and bulk model inference.
- Experience with ML model development.
- Experience applying ML solutions to products.
- Passionate about development efficiency and productivity.
Nice To Haves
- Experience building internal tooling for ML developers
Responsibilities
- Collaborate with the perception, planner, simulation and research teams to understand their modeling needs to shape solutions to improve dataset quality both in terms of distribution, label representation and quality.
- Partner with various Waymo infrastructure teams to provide a golden path to do data selection.
- Apply state-of-the-art techniques in data selection to reduce the amount of logged data that models at Waymo needs to train on.
- Develop ML models to automatically detect human label quality issues and send them in for correction.
- Build tooling to allow ML Engineers to experiment with signals that will be deployed to do log collection and label eval.
- Deploy automated flywheels to automatically improve the datasets across all relevant dimensions.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
Number of Employees
501-1,000 employees
