Senior Robotics Manipulator Engineer (Sensor & Perception)

Your Mission

This position is responsible for developing and implementing computer vision and deep learning solutions for robotic automation systems and actuation applications. The role involves designing and optimizing data processing workflows, 2D/3D vision systems, object detection, and pose estimation for pick-and-place and pick-and-assemble applications.

What To Expect

• Design and develop computer vision and AI-driven algorithms for object recognition, pose estimation, and grasp stability.
• Develop 2D and 3D vision pipelines using depth cameras, low-cost RGB cameras, and other sensors.
• Train and optimize deep learning models (e.g., CNNs, Transformers, PointNet) for robotic manipulation.
• Implement grasp pose generation, ranking, and validation algorithms to improve grasp success rates.
• Integrate solutions with other robotic modules for real-world pick-and-place and assembly applications.
• Enhance computer vision solutions and AI models for low-latency inference and industrial deployment.
• Develop data collection, annotation, and dataset expansion strategies to improve pick-and-place reliability.
• Study and implement pick-and-place and pick-and-assemble strategies and algorithms.
• Conduct validation tests to ensure the sensing and perception system meets industrial performance standards.
• Document technical reports, program code, and setup manuals.

What You'll Bring

• A Master's or Ph.D. degree in Electrical, Mechanical, or Computer Engineering or a relevant discipline, with more than five years of industry experience.
• Extensive experience in computer vision, deep learning, and 3D perception for robotic grasping.
• Proven ability to develop and deploy custom pick-and-place or pick-and-assemble applications.
• Strong background in grasp pose estimation, ranking, and pose validation techniques.
• Hands-on experience with sensor configuration and camera calibration.
• Proficiency in AI frameworks such as TensorFlow and PyTorch, along with deep learning model optimization techniques.
• Familiarity with image and point cloud processing libraries (e.g., OpenCV, PCL) and object detection toolkits such as MMDetection, Detectron2, or similar platforms.
• Proficiency in programming languages such as Python, C/C#/C++.
• Good understanding of MLOps principles, including model versioning, deployment pipelines, and monitoring.
• Any patents, publications, specialist certifications, or awards in robotics and automation are an added advantage.