计算机视觉开发工程师

Mission:

工作任务：

- Develop and optimize computer vision algorithms to enable robots to perceive, understand, and interact with their environment.

- Integrate vision systems with AI, motion control, and cloud services for robust real-time performance.

- Collaborate with hardware, AI, and embedded teams to ensure efficient deployment of vision models on embedded or edge devices.

- Continuously improve perception capabilities through data-driven development, testing, and tuning.

- 开发和优化计算机视觉算法，使机器人能够感知、理解周围环境并与之交互。

- 将视觉系统与人工智能、运动控制和云服务相集成，以实现强大的实时性能。

- 与硬件、人工智能和嵌入式团队合作，确保视觉模型在嵌入式或边缘设备上高效部署。

- 通过数据驱动的开发、测试和调优，持续提升感知能力。

-

Main Responsibilities:

主要职责：

- Design and implement algorithms for object detection, recognition, tracking, and scene understanding.

- Develop 2D and 3D vision pipelines using RGB, depth, LiDAR, and multi-camera setups.

- Optimize vision models for real-time inference on embedded platforms (GPU, TPU, VPU, DSP).

- Build data collection and annotation pipelines for training and validating vision models.

- Integrate computer vision modules with the robot software stack (ROS/ROS2 or custom frameworks).

- Ensure robustness in challenging conditions (variable lighting, occlusion, moving backgrounds).

- Collaborate with AI/ML engineers to deploy and maintain models in production.

- Test and validate perception features on real robotic platforms and in simulation.

- Maintain documentation, code quality, and version control for long-term maintainability.

- 设计和实现用于目标检测、识别、跟踪和场景理解的算法。

- 利用 RGB、深度传感器、激光雷达和多相机设置开发二维和三维视觉处理流程。

- 优化视觉模型，以在嵌入式平台（GPU、TPU、VPU、DSP）上实现实时推理。

- 构建用于训练和验证视觉模型的数据收集和标注流程。

- 将计算机视觉模块与机器人软件栈（ROS/ROS2 或自定义框架）相集成。

- 确保在复杂环境条件下（光线变化、遮挡、背景移动等）的稳定性。

- 与人工智能 / 机器学习工程师合作，在生产环境中部署和维护模型。

- 在真实机器人平台和仿真环境中测试和验证感知功能。

- 维护文档、保证代码质量并进行版本控制，以确保长期可维护性。

-

Skills Required:

所需技能：

Technical:

专业技术技能：

-Strong experience in C++ and Python

-Experience using computer vision libraries (OpenCV, Open3D, PCL)

-Knowledge of AI/ML frameworks (PyTorch, TensorFlow, ONNX…)

-Familiarity with model optimization for embedded systems (GPU, TPU, NPU…)

-Experience in data management & annotation (dataset creation, cleaning, labeling)

-Understand 3D data processing, point clouds, and SLAM.

-knowledge of data augmentation and synthetic data generation for training models.

具备扎实的C++ 和 Python 使用经验

有使用计算机视觉库（OpenCV、Open3D、PCL）的经验

了解人工智能/ 机器学习框架（PyTorch、TensorFlow、ONNX 等）

熟悉嵌入式系统（GPU、TPU、NPU 等）的模型优化

有数据管理和标注经验（数据集创建、清理、标记）

理解三维数据处理、点云以及同步定位与地图构建（SLAM）

了解用于模型训练的数据增强和合成数据生成

Soft Skills:

软技能：

-Problem solving oriented thinking and delivery-focused execution

-Excellent communication skills across technical and non-technical audiences

具备以解决问题为导向的思维和注重成果交付的执行力

能够与技术和非技术人员进行良好沟通

Languages:

语言能力：

Professional proficiency in French and English

法语和英语达到专业熟练水平

Education:

教育背景：

Master’s or PhD in Computer Vision, Robotics, AI, or related fields.

计算机视觉、机器人学、人工智能或相关领域的硕士或博士学位

Experience:

工作经验：

2 years in computer vision development, preferably in robotics or autonomous systems.

2 年计算机视觉开发经验，有机器人或自主系统相关经验者优先

Base 武汉；月薪：20~30k