Senior Manager, Perception Data

The role

Lead the perception data organization, including data science, data engineering and data labeling. Own the learning loop that turns real-world fleet data into better driving models.

What you will do

• Own the perception data flywheel from fleet signals and model behavior through training, evaluation and measurement
• Lead and develop a team of 10+ across data science, data engineering and data labeling
• Drive auto annotation and auto labeling pipelines to reduce manual cost and improve label quality
• Build data miners that surface rare, surprising and safety critical scenarios in very large datasets
• Define how fleet logs are selected, stored and retrieved for models
• Establish how the value of data is measured and make trade-offs across quality, accuracy, speed, cost and scale
• Feed curated data into model training and evaluation, then analyze outcomes to refine collection and labeling
• Work with ML, metrics and evaluation, and infrastructure teams

Required qualifications

• Track record of building and leading high-performing technical teams, including managing managers or senior individual contributors
• Deep technical expertise in computer vision, video, multimodal AI or related perception problems
• Experience leading large-scale data capabilities that directly influence model training, evaluation and performance
• Strong intuition for data value, with experience in data discovery, selection, curation and enrichment at scale
• Proven execution at scale with strong technical and commercial judgment
• Ability to move between strategy and technical detail, set direction in ambiguity and influence senior stakeholders

Nice to have

• Autonomous driving, robotics or embodied AI
• Large-scale video, multimodal or foundation model training
• Semantic search, embeddings, active learning, auto labeling or intelligent data selection
• Large-scale real-world data acquisition across fleets, partners or multiple geographies

About the company

Zoox develops robotaxis that rely on perception data to understand the world and drive safely. The company focuses on learning from real-world urban driving data.