Computer Vision Engineer (Object Detection & 3D Pose Estimation)

Tokyo, Japan (MJHQ)

1 - Software Development – Computer Vision Team /

Full-Time (English) /

On-site

Mujin develops "MujinController," a platform that leverages a real-time digital twin and advanced robotics to seamlessly connect industrial equipment for fully autonomous operations.

Driven by our unique approach towards Robotics Machine Intelligence (MujinMI), we offer a robust suite of perception, planning, and control algorithms, enabling autonomous robot movement and transforming automation in challenging industrial environments.

Trusted by globally recognized companies, our cutting-edge technology enhances efficiency and innovation across the supply chain. With headquarters in Japan and expanding offices in China, the US, and Europe, Mujin offers a dynamic, fast-growing environment where your work directly shapes the future of automation.

As a Computer Vision Engineer, you will be a part of the Mujin R&D team, focusing on the algorithmic design, development, and deployment of computer vision applications for high-speed recognition and the world’s first 3D vision system for factory automation and logistics solutions.

An article for you to understand more about 3D computer vision in Mujin:

Unlocking the potential of Vision Engineering: beyond deep learning for industrial robotics

Responsibilities

・Solve cutting-edge scientific and technical challenges related to recognition and pose estimation of a very wide variety of objects in challenging scenarios

・Analyze and evaluate state-of-the-art algorithms related to detection and pose estimation, from academic and industrial research, and implement and enhance them in a production environment

・Design, develop and evaluate the performance of highly scalable and accurate real-time computer vision applications, in Python and C/C++

・Perform the detailed test, carry out performance analysis on algorithms, and use continuous integration tools to finely enhance the rapidly deployed algorithms

Minimum Requirements

Graduating/ Graduated Computer science or relevant faculty in BS, MSc or Ph.D.
BS or MS with computer vision experience or Ph.D. in Computer Vision related topics
The ability to develop applications and tools in Python and/or C＋＋
Technical communication skills in English (reading and writing)

Preferable Requirements

3D pose estimation of textured and textureless objects in cluttered scenes, with proven experience
Python and C++ experience
Experience with a vast set of computer vision libraries
Mathematical background
Previous contributions to open source projects
Extras: object tracking, SLAM, computer graphics, augmented reality, machine learning, exposure to projects in robotics

Attractiveness

We are hiring to expand the team! If you would like to apply real-time computer vision algorithms to robotics and join the industrial automation revolution, this role is for you!
Our computer vision algorithms must be robust to run on 24/7 systems for thousands of items per customer, for diverse customers and applications. We must continue to enlarge its capabilities toward more autonomy, scalability, and diversity of applications.
The current team members have done research in the world’s top-tier universities and labs in robotics, computer vision, and image and signal processing, such as at Carnegie Mellon University and Stanford University. They have also worked in other industries like robotic inspection and automotive.

Interview Process:

HR Interview: Discussion with Human Resources.
Hiring Manager Interview (Whiteboard interview): One or two rounds with the hiring manager. Check this link for more information about the technical interview.

#LI-Onsite

Location

3-8-5 Tatsumi, Koto-Ku, Tokyo 135-0053, Japan

Work Hours

8:45 - 17:45 (with a 60-minute break)

Salary

・Based on experience and skills

・Salary revision twice a year

・Additional bonuses available based on performance

Holidays

・Every Saturday and Sunday

・Annual paid leaves