As a University of Applied Learning, SIT works closely with industry in our research pursuits. Our research staff will have the opportunity to be equipped with applied research skill sets that are relevant to industry demands while working on research projects in SIT.

We are seeking a Robotics Software Engineer with strong experience in learning-based control and mobile manipulation. The successful candidate will work on algorithm development for contact-rich robotic manipulation, integrating perception, planning, and control within a real-world robotic system.

Job Responsibilities：

• Develop, implement, and optimize algorithms for contact-based mobile manipulation.
• Apply reinforcement learning, imitation learning, and motion / manipulation skill learning to real robot tasks.
• Integrate learned policies with the robot control stack in ROS / ROS2 environments.
• Develop perception and state representation pipelines using RGB-D / 3D sensing.
• Conduct simulation-to-real deployment, including data collection, model training, and policy testing.
• The staff to to communicate with any relevant internal or external stakeholders to ensure project deliverables can be met.
• Any other ad-hoc duties assigned by supervisor.

Job Requirements：

• Bachelor’s degree or above in Robotics, Computer Science, Mechanical Engineering, Control Engineering, or related fields.
• Hands-on experience with deep learning frameworks such as PyTorch or TensorFlow.
• Experience with ROS or ROS2 for real robot software integration.
• Proficient in Python and C++, with experience in writing production-level code.
• At least 2 years of experience in robotics project development (research or industry).
• Working knowledge in reinforcement learning, imitation learning, or learning-based control.

Preferred Qualifications：

• Experience deploying algorithms on mobile manipulators or articulated robot arms.
• Familiarity with simulation tools (e.g., Gazebo, Isaac Sim, MuJoCo).
• Knowledge of control / motion planning frameworks such as MoveIt  or whole-body control libraries.