Robotic Perception Intern – Arms (human)

Give Our Robots Sight and Touch

Perception is where a robot's intelligence starts. In our AI/Perception team, you'll work on the algorithms that turn raw camera, depth, and force data into something a robot can act on — detecting and tracking objects, reconstructing 3D scenes, and fusing sensors into a coherent picture of the world, fast enough to matter in real time. Our robots are built to work alongside people in environments that never hold still, so this isn't benchmark work: your models run on real hardware, next to real humans, and have to hold up when the lighting is poor and the scene changes mid-task. You'll collaborate closely with software, hardware, and product teams, and see your work land in our products. If you want to spend your internship on perception problems that don't have clean answers yet, this is the place.

Your Mission & Challenges

We are looking for a motivated and talented Robotic Perception Intern to join our AI/Perception team. This internship will give you hands-on experience helping our robots see, understand, and interact with dynamic, shared workspaces. You will work on deep-learning perception models and parts of the sensor fusion and perception stack for our collaborative robot arms.

You will contribute to areas such as:

Perception pipeline: Work on modules along the full perception path — from raw sensor input (RGB and depth cameras, force/torque, joint sensors) through sensor fusion, object detection and tracking, 3D reconstruction, and scene understanding — to help build the workspace models our arms rely on for grasp planning, manipulation, and safe interaction with the people working next to them.

Deep learning for perception: Implement, train, and fine-tune neural networks for perception tasks (e.g. object recognition, detection, tracking) and support their deployment on the robot.

Computer vision & 3D: Create and optimize computer vision algorithms for real-time use, including classical vision (OpenCV), 3D geometry, and point-cloud processing.

Real-time software: Implement perception software in Python and modern C++, using GPU acceleration where it matters.

What We Can Look Forward To

Education: Currently pursuing or recently completed a degree in Computer Science, Robotics, Electrical Engineering, or a related field

Programming skills: Proficiency in programming languages such as Python or C++

AI frameworks: Familiarity with AI frameworks and libraries (e.g. PyTorch, TensorFlow)

ML & CV foundations: Understanding of machine learning and computer vision concepts and techniques

Perception exposure: Interest in or exposure to robot perception: RGB-D cameras / force-torque sensing, OpenCV, 3D geometry, or sensor fusion (academic projects, coursework, or personal work welcome)

Mindset: Strong problem-solving and analytical skills

Communication: Your communication skills make you shine

Language: You have a perfect command of the English language