Senior ML Engineer - HD Mapping & Scalable Pipelines

Socket.dev; San Francisco (CA); Hybrid; USD 213,000 - 263,000; Full time

Benefits offered by this job

Discretionary annual bonus

Equity incentive plan

Benefits program

Job summary

Waymo is seeking an experienced engineer to advance the Waymo Driver by building and evaluating machine learning models that convert raw sensor data into precise HD maps. You will collaborate with onboard teams to refine mapping formats, run large-scale experiments, and measure impact on end-to-end mapping pipelines.

You will design and implement scalable data processing workflows in distributed systems, driving reliability and performance as we push global coverage of autonomous mapping.

Qualifications

• BS in Computer Science or a similar technical field or equivalent practical experience.
• Hands-on experience with statistical analysis, experiment design, and quantitative evaluation of ML models or data pipelines.
• Experience building scalable data processing pipelines using distributed frameworks like Google Data Flow or Apache Beam.

Responsibilities

• Evaluate and launch machine learning models that automatically generate maps from raw data.
• Collaborate with onboard teams to evolve mapping formats for automation.
• Apply statistical analysis to validate large-scale changes.
• Build backend infrastructure for storing and processing map data.
• Scale systems to support mapping the whole world.

Skills

Statistical analysis

ML data pipelines

Distributed processing

Ownership mindset

Software engineering

C++ optimization

Education

BS in Computer Science or equivalent practical experience

MS/PhD in CS/ML/Robotics or related field (preferred)

Tools

Google Data Flow

Apache Beam

Job description

Waymo is seeking an experienced engineer to advance the Waymo Driver by building and evaluating machine learning models that convert raw sensor data into precise HD maps. You will collaborate with onboard teams to refine mapping formats, run large-scale experiments, and measure impact on end-to-end mapping pipelines.

You will design and implement scalable data processing workflows in distributed systems, driving reliability and performance as we push global coverage of autonomous mapping.