Назад
Company hidden
2 месяца назад

Robotics Automation Perception Engineer (JP-Retail)

Формат работы
hybrid
Тип работы
fulltime
Грейд
middle
Английский
b2
Страна
Japan
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Robotics Automation Perception Engineer (JP-Retail) (Computer Vision/Deep Learning): Developing perception systems for the Ghost robot to automate pick-and-place operations in Japanese convenience stores with an accent on sensor fusion, robust algorithm development, and deployment on constrained hardware. Focus on improving quantitative success rates, optimizing and compressing models, and solving perception challenges in dynamic retail environments.

Location: Tokyo, Japan; hybrid workplace

Company

hirify.global develops the custom-built Ghost robot to automate pick-and-place operations in Japanese convenience stores and reshape retail operations through robotics.

What you will do

  • Develop perception software for a custom-hardware automation system using deep learning, computer vision, and control algorithms.
  • Use RGB, depth, and other sensor data from deployed robots to improve perception performance in dynamic retail environments.
  • Research, refine, implement, and continuously improve perception algorithms based on quantitative outcomes.
  • Optimize and compress deployed models for speed, latency, and efficient execution on constrained hardware.
  • Collaborate with automation engineers, translate executive priorities into actionable tasks, and manage delivery timelines.
  • Analyze problems and data, debug issues, and deploy robust and safe systems.

Requirements

  • At least 3 years of experience developing perception systems or equivalent academic research experience.
  • Quick and accurate problem-solving skills, with strong debugging and issue-monitoring capabilities.
  • Extensive experience in low-level computer vision, machine learning, and deep learning, including implementing state-of-the-art methods from scratch.
  • Proficiency in Python and commonly used libraries including PyTorch, OpenCV, NumPy, and SciKit.
  • Experience working with RGB and depth sensors or multi-sensor setups such as RGB plus LiDAR.
  • Familiarity with data augmentation techniques.
  • Experience customizing deep learning applications for object detection and segmentation, keypoint detection, and 3D pose estimation and reconstruction.
  • Experience optimizing model performance for speed and latency, including network layer optimization and TensorRT or TorchScript.

Nice to have

  • Experience with Open3D, Point Cloud Library, MMDetection, FastAI, or similar libraries.
  • Proficiency in modern C++ such as C++11, C++14, or newer.
  • Experience with ROS, camera calibration, and hand-eye calibration.
  • Research experience in computer vision, AI, or robotics, including publications at venues such as CVPR or ICRA.
  • Experience generating synthetic datasets and using domain randomization with Blender, OpenGL, Isaac Sim, MuJoCo, or similar tools.
  • Experience working with manipulators.
  • Background in startups or fast-paced environments.
  • Engineering experience in motion planning and execution, signal processing, or network communication such as pub/sub and req/rep.

Culture & Benefits

  • Full-time employee position.
  • Hybrid workplace in Tokyo.
  • Work on custom robotics hardware deployed in real-world Japanese retail environments.
  • Collaborate with automation engineers on company objectives and executive priorities.

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 →