- Redwood City, California, United States
Lead evaluation research for embodied AI and world models, designing benchmarks, metrics, and validation pipelines.
Responsibilities
- Run ablations and benchmark open-source world models and robotic policies
- Validate raw data to flag low-quality captures
- Set direction for evaluation research agenda
- Invent benchmarks, metrics, and methodologies
- Run end-to-end model evaluation from offline studies to live deployment
Requirements
- PhD in Computer Science, Machine Learning, Robotics, Computer Vision, or closely related discipline