Staff Machine Learning Engineer, Tech Lead, Labeling Automation

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 DriverTM—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.

As a Staff Software Engineer (L6) on the Labeling Team, you will lead the technical strategy for automating our data pipelines.

You will build cutting-edge auto-labeling systems to drastically scale our throughput and develop intelligent auto-graders to guarantee exceptional data quality.

This is a high-impact leadership role where you will train, deploy, and orchestrate state-of-the-art computer vision architectures and Vision-Language Models (VLMs) to solve complex semantic labeling challenges across our massive autonomous driving fleet.

In this hybrid role, you will report to a Technical lead Manager, Staff Software Engineer.

You will:

• Architect and Scale Auto-Labeling: Lead the design and deployment of highly scalable auto-labeling pipelines that significantly improve data throughput and reduce our reliance on manual annotation bottlenecks.
• Build Robust Auto-Graders: Develop automated anomaly detection and quality evaluation systems (auto-graders) to assess annotation accuracy, detect regressions, and enforce rigorous quality standards across millions of labels.
• Train & Deploy SOTA Computer Vision Models: Train, optimize, and push into production advanced 2D and 3D computer vision models. You will utilize architectures ranging from foundational zero-shot models like SAM (Segment Anything Model) and efficient real-time detectors like YOLO, to bespoke 3D perception and tracking models.
• Leverage Vision-Language Models (VLMs): Fine-tune, and deploy large VLMs and LLMs, utilizing prompt optimization and advanced post-training techniques (SFT, RL, etc.), to solve complex, open-set labeling and contextual reasoning tasks.
• Drive Technical Direction: Act as a technical pillar for the Labeling organization. Set the long-term ML strategy, guide architectural decisions, and mentor senior and mid-level engineers.