Senior Software Engineer, Model Lifecycle

Core Challenge

The core challenge within Model Lifecycle is accelerating Waymo's ML development cycle. As we scale to new cities and vehicle platforms, our data volume is exploding, and our models are becoming more complex, handling more and more tasks.

Responsibilities

• Design, build, and maintain scalable data pipelines to process many petabytes of complex sensor data, making it ready for efficient model training and evaluation.

• Develop infrastructure to produce reliable, high-quality datasets for a wide range of ML models, from real-time on-car models to large-scale offboard foundation models.

• Build towards an automated, unified data flywheel -- a datagen and ingestion solution that seamlessly connects data curation to model training.

• Develop infrastructure for Perception-wide model training and release-ready packaging, ensuring the model development lifecycle is robust, efficient, and reproducible.

• Maintain and support critical data generation infrastructure and data refreshes for the Perception team.

• Automate data quality and validation checks to ensure the integrity, consistency, and trustworthiness of our datasets as we scale to new cities and vehicle platforms.

• Collaborate closely with ML engineers, research scientists, and core infrastructure teams to understand user needs and deliver impactful ML workflows.

Requirements

• Outstanding programming skills in C++ or Python

• Experience in ML data engineering, including data pipelines, data curation, data balancing, etc.

• Experience with the ML development lifecycle, including data engineering, model training, model evaluation, and model deployment.

• BS/MS and 5+ years of industry experience, or PhD + 2 years of industry experience

• Passionate about data-centric AI and autonomous driving applications

Preferred

• Experience in working in cross-functional settings to support data users and collaborating with infrastructure stakeholders

• Customer-oriented mindset

• Hands-on experience in building large scale data processing or retrieval systems and pipelines: Apache Spark, Apache Beam, Google Cloud Dataflow, AWS Data Pipeline, Faiss/ScaNN, etc.

• Experience building automated ML pipelines -- data pipelines, continuous model training/evaluation pipelines, etc.

Benefits

Benefits for this role include:

• Health, dental, vision, life, disability insurance

• Retailment Benefits: 401(k) with company match

• Paid Time Off: 20 days of vacation per year, accruing at a rate of 6.15 hours per pay period for the first five years of employment

• Sick Time: 40 hours/year (statutory, where applicable); 5 days/event (discretionary)

• Maternity Leave (Short-Term Disability + Baby Bonding): 28-30 weeks

• Baby Bonding Leave: 18 weeks

• Holidays: 13 paid days per year