Spring 2027 Robot Learning R&D Co-op (Robotics)

Location: Onsite at the Bedford, Massachusetts office, United States. The co-op runs approximately from January to June 2027, with flexible dates.

Company

Develops robotics systems that apply robot learning and manipulation technologies to real-world challenges.

What you will do

• Build infrastructure to integrate, deploy, and evaluate learning-based manipulation capabilities.
• Train and adapt machine learning architectures for robot learning and visual scene understanding.
• Improve the robot learning data collection application.
• Process, validate, visualize, and evaluate system logs, sensor data, annotations, and failure cases from on-robot policy execution.
• Integrate grippers and other hardware into perception, planning, and robot-control systems.
• Use production data and internal development systems to implement and evaluate solutions across the robotics stack.

Requirements

• Currently pursuing an advanced degree in Robotics, Machine Learning, Computer Science, or a closely related field.
• Strong software development expertise in Python.
• Experience with modern machine learning methods, such as imitation learning, reinforcement learning, generative models, or vision transformers.
• Experience applying machine learning models to systems that interact with the physical world.
• Experience developing robotics software with Linux, Ubuntu, and ROS.

Nice to have

• Experience with C++.