Robotics Software Internship, Manipulation

• Job Title: Robotics Software Internship, Manipulation
• Department: Software Engineering
• Reports To: Manipulation Lead
• Employment Type: Internship
• Location: Houston, Texas – Required (on-site)
• Help design and implement dexterous manipulation algorithms for humanoid robots with high-DOF, multi-fingered hands, working closely with senior engineers.
• Contribute to the manipulation pipeline (perception, grasping, trajectory optimization, motion planning, and control) on tasks like precise grasping, dual-arm manipulation, and in-hand object manipulation.
• Support the implementation and testing of control strategies for dexterous manipulation, including force/motion control and visual/tactile servoing.
• Assist with integrating manipulation components into the humanoid robot's whole-body controller and loco-manipulation efforts.
• Build and iterate on digital-twin simulation environments for algorithm development using simulators such as MuJoCo and Isaac Sim.
• Run and help design tests in both simulated and real-world environments, and help analyze the results.
• Partner with the machine learning team to help train and deploy models for advanced manipulation tasks.
• Stay current on manipulation research and bring relevant ideas, traditional and deep learning-based, back to the team.
• Currently pursuing a BS, MS, or PhD in Robotics, Computer Science, Mechanical/Electrical Engineering, or a related field.
• Coursework, lab research, or project experience (capstone projects, robotics competitions, personal projects) involving control and manipulation of robotic or humanoid arms.
• Foundational knowledge of motion planning, control theory, and optimization.
• Programming proficiency in C++ and/or Python.
• Exposure to relevant robotics libraries or tools (e.g., ROS, MoveIt!, Drake, OpenRAVE) through coursework or projects.
• Familiarity with deep learning fundamentals as applied to robotics or manipulation.
• Some exposure to computer vision concepts, such as sensors, point clouds, segmentation, and object detection, through coursework or projects.
• A strong desire to learn quickly and contribute in a fast-paced startup environment.
• Project or research experience with contact modeling, force/torque estimation, or tactile sensing for dexterous tasks.
• Exposure to machine learning for dexterous manipulation, such as learning-based grasp strategies, behavior cloning, or reinforcement learning.
• Published research related to manipulation.

None flagged.