Perception Machine Learning Engineer - Continuous Learning

Waymo is an autonomous driving technology company with the mission to be the world's most trusted driver. As a Perception Machine Learning Engineer, you will build the intelligent systems that 'see' the world, directly shaping the future of autonomous travel. Within the Perception team, the company is tackling some of the most complex, open-ended challenges in autonomous driving. Models must constantly adapt and improve as the fleet encounters the vast, unpredictable realities of public roads. The role is the bridge between model architecture and large-scale data infrastructure, leveraging active learning and sophisticated data curation strategies to ensure perception models are always learning from the most informative examples. In this hybrid role you will report to a Technical Lead Manager.

Responsibilities

Architect Infrastructure: Design and scale the data pipelines needed to mine, ingest, and manage massive volumes of sensor data from the fleet; Drive Model Improvement: Deploy active learning algorithms to continuously identify and select the most impactful data for training, ensuring large models continuously adapt to new environments with incremental updates; Ensure Model Quality: Develop methods and recipes for evaluating real-world performance of models, detecting regressions in model updates, and developing and maintaining ground-truth free performance metrics; Optimize Data Efficiency: Conduct large-scale experiments focused on data balancing, subset selection, and label quality optimization, and lead automated curation strategies including smart pruning and downsampling; Solve Long-Tail Challenges: Develop robust mining, training and evaluation pipelines for rare, safety-critical real-world scenarios; Innovate with Model Signals: Utilize uncertainty estimation, confidence scores, and embedding space analysis to uncover model blind spots and guide automated data acquisition; Collaborate Cross-Functionally: Work closely with researchers and operations teams to iterate on the end-to-end model development lifecycle

Requirements

A bachelor's degree in Machine Learning, Robotics, or Computer Science; 3+ years of professional experience in Machine Learning and/or Computer Vision; Proven, hands-on experience applying active learning in production environments; Strong expertise in building large-scale ML data pipelines (mining, extraction, auto-labeling, ingestion); Deep understanding of data curation (balancing, core set selection, and sampling) to optimize model performance; Proficiency in Python and deep learning frameworks (PyTorch or JAX); Strong software engineering skills for writing robust, production-ready code

Nice to have

A record of publications at top-tier conferences (e.g., CVPR, ICCV, ECCV, ICML, ICLR, NeurIPS, IROS, RSS, AAAI, IJCV, PAMI); Experience with C++; Experience building data-centric infrastructure from the ground up to accelerate model iteration cycles; An advanced degree (MS or PhD) in Machine Learning, Robotics, or Computer Science

Benefits

Medical, dental and vision insurance; Mental wellness support; Gym membership and special wellness programs; Competitive compensation; Bonus opportunities; Discretionary annual bonus program; Equity and equity incentive plan; Employees provident fund; Other perks and employee discounts; Flexibility to work from another location for four weeks per year; Remote working opportunities; Paid time off; Bereavement, sick, and parental leave