Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
88
Крутая вакансия
развернуть
Чётко очерченная роль сочетает современные технологии компьютерного зрения с внедрением на реальных логистических роботах и даёт сильный продуктовый опыт в перспективной AI-сфере.
Современный стек
Роботы в деле
Перспективная робототехника
?Работа в Токио
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Robotics Perception Engineer (Logistics) (Computer Vision/Deep Learning): Developing perception systems for custom-made manipulators that automate logistics operations in real-world warehouses with an accent on object detection, 3D perception, sensor data, and real-time model optimization. Focus on building and deploying C++ and Python algorithms, integrating perception with robot control, and improving production success rates through field-failure analysis.
Location: Hybrid in Tokyo, Japan
Company
hirify.global develops robotics products for automating logistics operations with custom-made manipulators.
What you will do
Develop and improve perception modules for logistics automation, including object detection, segmentation, keypoint detection, 3D pose estimation, and 3D reconstruction.
Implement perception software in modern C++ and Python and integrate it with robot control and system software.
Collect and curate RGB, depth, and other sensor data from operating robots, then improve algorithms using quantitative results.
Optimize and compress deployed models for real-time inference on limited compute.
Investigate logs, metrics, tests, and field failures; deliver fixes and features end-to-end to improve production success, safety, and stability.
Collaborate with motion planning, system integration, and hardware engineers while managing tasks and timelines independently.
Requirements
Master’s degree or above in Computer Science, Robotics, or a relevant field.
3+ years of experience developing perception systems or equivalent research experience.
Proficiency in both modern C++ (C++14 or above) and Python.
Strong understanding of low-level computer vision, machine learning, and deep learning, including implementing state-of-the-art methods from scratch.
Hands-on experience with most of the following: object detection, segmentation, keypoint detection, 3D pose estimation, 3D reconstruction, RGB/depth and multi-sensor setups, model optimization, and real-time inference.
Experience with relevant libraries and tools such as PyTorch, mmdetection, fastai, OpenCV, Open3D, Point Cloud Library, TensorBoard, MLflow, or Weights & Biases.
Quick and accurate problem-solving, careful issue monitoring and debugging, a product mindset, proactive collaboration, and good communication skills.
Business-level English required.
The role does not require a candidate to meet 100% of the listed criteria; matching most requirements is sufficient to apply.
Nice to have
Japanese language skills for communication with internal and external stakeholders.
Experience deploying and maintaining perception systems on real-world robots, including ROS or ROS2.
Knowledge of camera and hand-eye calibration.
Experience with domain randomization and synthetic data generation using OpenGL, Blender, Isaac Sim, MuJoCo, or similar tools.
Research experience in computer vision, AI, or robotics, including publications at CVPR, ICRA, or similar venues.
Experience with manipulators, motion planning, and execution.
Experience with signal processing, network communication, Docker, CI/CD, and automated deployment of ML models to robots.
Startup work experience.
Culture & Benefits
Full-time employee position.
Work directly on a product used in real logistics operations.
Collaborate across perception, motion planning, system integration, and hardware teams.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →