Machine Learning Research Engineer/Scientist

You will develop software and algorithms that enable robots to complete dexterous manipulation tasks in home environments. You will use real-world data and fleet feedback to develop behaviors, curate data, train and evaluate models, deploy them on robots, and write production-quality code.

Responsibilities

• Design and develop robot learning algorithms for manipulation and controls
• Use large-scale real-world data to develop generalizable robot behaviors
• Own task definition, data curation, model training, evaluation, and on-robot deployment
• Collaborate on consumer personal robot development
• Write maintainable production-quality code

Requirements

• 3+ years or equivalent experience in machine learning for robotics, controls, or perception
• Proficiency with Python and a deep learning framework
• Experience with robot learning for real-world tasks, including offline and online training and evaluation
• Experience implementing visualization, debugging, and evaluation tooling for data and learning pipelines
• Communication and cross-functional collaboration skills

Benefits

• Equity