Staff Machine Learning Engineer, Perception, Sensor Pipelines

Software Engineering builds the brains of Waymo's fully autonomous driving technology. Our software allows the Waymo Driver to perceive the world around it, make the right decision for every situation, and deliver people safely to their destinations. We think deeply and solve complex technical challenges in areas like robotics, perception, decision-making and deep learning, while collaborating with hardware and systems engineers. If you’re a software engineer or researcher who’s curious and passionate about Level 4 autonomous driving, we'd like to meet you.

The Sensor Pipelines team applies sensor fusion and ML approaches to address critical challenges in Perception; like detections of Collisions, Antagonistic Behaviors like Vandalism, Sensing Occlusions, etc. Our work involves cutting-edge research (Gen AI) to solve real-world problems and requires close collaboration with onboard teams across Alphabet. We have access to millions of miles of driving data from a diverse set of sensors, enabling engineers like you to develop sophisticated models and techniques at scale. For this specific position, we are seeking an experienced MLE to be our data TL, build robust data pipelines and data flywheel for the team, through collaboration cross-team with Perception, Behavior, ML foundation and Simulation teams.

This role follows a hybrid work schedule and reports to a Technical Lead Manager.

You will:

• TL the team to build data platforms for large-scale evaluation of the systems. Create data sets, recipes for human and machine labeling, methods and recipes for continuous logging, data intake, selection and incremental updates of models, stream eval data set curation, sampling & slicing, enable data-driven decision making, develop methods for logging, data mining and recipes for automated data collection/model update flywheels.
• Define long-term strategy, develop roadmaps, and guide the team to execute projects from ambiguous requirements to high-impact deliverables.
• Collaborate with team members in understanding their data needs & build infra solutions that solve their problems. Collaborate with the eval team to enable smooth, robust and efficient evaluation on top of the data platform.
• Collaborate cross-team, exercise complete end-to-end ownership in delivering a robust and adaptable data platform jointly w/ collaborating teams. This platform will be capable of supporting rapid iteration and meeting the demanding timelines associated with Waymo's city expansions, enabling proactive problem-solving.

You have:

• Bachelor’s in Computer Science or a similar discipline, or an equivalent amount of deep learning experience
• 8+ years of experience designing and building complex, scalable systems.
• Demonstrated technical leadership in defining long-term strategy, developing roadmaps, and guiding teams to execute projects from ambiguous requirements to high-impact deliverables.
• Demonstrated ability to work effectively across diverse teams and communicate technical concepts clearly.
• Deep expertise in the evaluation of Machine Learning systems at scale, encompassing metrics design, rigorous experimentation, large-scale data analysis, and statistical methods.
• Excellent problem-solving skills, clear technical communication, and a strong sense of end-to-end ownership.

We prefer:

• Master’s or PhD in Computer Science or a similar discipline, or an equivalent amount of deep learning experience
• Familiarity with autonomous vehicle systems, particularly Perception, including typical data pipelines and evaluation processes.
• Hands-on experience with data analysis, visualization, and triage tools & workflows, with a knack for identifying improvement areas.
• Experience in designing and implementing efficient data processing workflows for large datasets.
• Publications at top-tier conferences like CVPR, ICCV, ECCV, ICLR, ICML, ICRA, IROS, RSS, NeurIPS, AAAI, IJCV, PAMI.
• Experience with C++.