|職務内容||This role focuses on the automation of custom-made manipulators, aiming to automate convenience store and logistics operations without human intervention to a high success rate, by developing perception modules.
Our main focus is to productize the world’s first robot and its perception system to be integrated into the convenience store, logistics and so on. We use a variety of technologies to achieve our goals, from traditional (e.g. computer vision, machine learning) to state-of-the-art (deep learning, reinforcement learning) and expect you to have a similar mindset. Teamwork, flexibility, and quick learning are key soft skills as well.
- Contribute to the development of an automation system using custom hardware, by developing sophisticated software engineering to do perception, with Deep learning, OpenCV, ROS and so on.
- Leverage Python and C++, develop a custom perception software towards the automation solution.
- Work with other automation engineers and achieve goals set by CxOs .
- Architect the solution with the team, and deploy fast.
- Break up vague goals into concrete steps and manage your own timeline to achieve company goals.
- Collect data, analyze results, and continuously improve algorithms quantitatively.
- Productization experience
- Complex problem solving skills
- Careful issue monitoring / debugging skills
- Strong experience in implementing complex hardware / software combined system with ROS or equivalent.
- Experience in fields such as computer vision, 3d computer vision, machine learning, and deep learning, as well as experience of implementing state-of-the-art methods from scratch.
- Proficiency in modern Python and C++ (over C++14), along with software architecting skills.
- Experience in linear algebra and 3D perception or equivalent (such as computer graphics)
- Strong experience in deep learning applications (keypoint detection, grasp estimation, 3d reconstruction etc) for real product application
-- using pytorch, tensorflow, caffe, etc
- Experience in network / performance optimization
-- network layer optimization
-- TensorRT / TorchScript etc
- Knowledge about camera calibration / hand-eye calibration.
- Engineering experiences with one or more of the following
-- Filtering (Kalman Filter, Particle Filter, MeanShift etc)
-- network communication (pub/sub, req/rep, etc)
-- Domain randomization using OpenGL, Unity, Unreal Engine, Blender etc
- Research experience in CV / AI and related robotics field (CVPR / ICCV / ECCV / ICRA / IROS)
- Working with custom made manipulators
- Work experience in startups
- Experience working with manipulators
- Experience in motion planning, collision avoidance, and path following of robots
- Work experience with game engines such as Unity, Unreal Engine