About The Internship
Berkshire Grey is a leader in the field of AI and robotics, providing innovative solutions for e-commerce, retail replenishment, and logistics. Our technology automates complex pick, pack, and sort operations.As part of the Research & Advanced Development group, you will research and develop new approaches to solving challenging manipulation problems for real-world robotics systems, allowing them to understand and interact with their environment in unprecedented ways. Your work will contribute to enhancing the capabilities of our robotic solutions and explore new solutions and approaches, unlocking new value we deliver to our customers.
This position offers a unique opportunity to work at the cutting edge of robotics applied to real-world challenges.We are seeking interns in a variety of disciplines related to perception/computer vision including:
- Unsupervised representation learning for visual understanding of manipulation tasks and policy learning
- AI systems (VLM, other) applied to various warehouse tasks, such as dealing with unexpected situations, dense packing, or error/damage detection.
- Few-view object reconstruction
- Generative AI for data generation/augmentation related to robot manipulation
- Real2sim from large scale production data for robot simulation
In this role you will:
- Perform applied research in robot learning to address real-world warehouse challenges
- Collaborate with other researchers and engineers to apply research findings to our robots
- Leverage production data and our internal development systems to implement and evaluate your solutions
Qualifications
- Currently pursuing an advanced degree (MS or PhD) in Robotics, Machine Learning, Computer Science, or a closely related field.
- Strong software development expertise in Python
- Demonstrated proficiency with major deep learning frameworks such as PyTorch
- Experience with modern machine learning methods for computer vision such as vision transformers, VLMs, diffusion models, or related.
- Exposure to developing ML models for hardware interacting with the real world
This role will be onsite at the Bedford, MA office.6110-IN2502TK
