视觉算法部署实习生

Caterpillar · Industrial · Wuxi, Jiangsu

The role involves assisting in the development and implementation of visual solutions for autonomous driving, focusing on integrating and debugging embedded systems and visual components. It requires implementing core perception capabilities like object detection and obstacle recognition using computer vision and deep learning, and optimizing embedded inference. The role also involves dataset construction, quality control, and performance evaluation.

What you'd actually do

Participate in the design of autonomous driving visual solutions, responsible for the integration, debugging, and testing of related embedded systems and visual components, and complete the selection and determination of the visual algorithm tool chain.
Implement core perception capabilities such as object detection, semantic segmentation, and obstacle recognition in autonomous driving scenarios based on computer vision and deep learning technologies.
Build and maintain autonomous driving datasets, conduct training data annotation quality control, model performance evaluation, and carry out acceleration and optimization of embedded inference.

Skills

Required

Familiarity with deployment, optimization, and verification processes of deep learning models on embedded platforms
Experience in model deployment on ROS2, DeepStream, ARM devices, and NVIDIA Jetson/Orin platforms is a plus
Experience using TensorRT, CUDA, cuDNN, ONNX Runtime for edge inference acceleration
Analysis and optimization of performance metrics such as latency, throughput, memory footprint, and power consumption
System-level debugging in Linux Embedded environments (drivers, cross-compilation, system services, Docker)
Collaboration with hardware teams for device configuration and verification
Familiarity with deep learning visual detection algorithms, frameworks, and tools (CNN, YOLO series, TensorFlow, PyTorch)
Proficiency in Python, C++ or other relevant languages
Good problem-solving and teamwork skills
Good communication skills

Nice to have

Experience in model deployment on ROS2, DeepStream, ARM devices, and NVIDIA Jetson/Orin platforms

What the JD emphasized

embedded systems
visual components
embedded inference

Other signals

deployment
embedded systems
optimization

Read full job description

Career Area:

Students and Graduates

Job Description:

**Your Work Shapes the World at Caterpillar Inc. **

When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it.

**职位名称：视觉算法部署实习生 **

职位概述：

协助开发和实施视觉方案在自动驾驶中的应用。

主要职责：

参与自动驾驶视觉方案的设计，负责相关嵌入式系统与视觉组件的集成、调试与测试，并完成视觉算法工具链的选型与确定。
基于计算机视觉和深度学习技术，实现自动驾驶场景中的目标检测、语义分割与障碍物识别等核心感知能力。
构建并维护自动驾驶数据集，进行训练数据标注质量控制、模型性能评估，并开展嵌入式推理的加速与优化工作。

任职资格：

计算机科学、电子工程、自动化或相关领域的学士或硕士学位。
熟悉深度学习模型在嵌入式平台上的部署、优化和验证流程，可在 ROS2、DeepStream、ARM 设备以及 NVIDIA Jetson/Orin 等平台上完成模型落地相关项目经验佳。
使用 TensorRT、CUDA、cuDNN、ONNX Runtime 等工具实现端侧推理加速，并根据需求对延迟、吞吐量、内存占用和功耗等性能指标进行分析与优化。
在 Linux Embedded 环境下进行系统级调试，包括驱动、交叉编译、系统服务和 Docker 等工作，并与硬件团队合作完成设备配置与验证。
熟悉深度学习视觉检测算法、框架和工具，如卷积神经网络（CNN）、YOLO系列算法、TensorFlow、PyTorch等。
具备良好的编程能力，熟练掌握Python、C++或其他相关语言。
具备良好的问题解决能力和团队合作精神。
具备良好的沟通能力，能够清晰地表达技术概念。
每周可实习4天以上，持续4个月以上。

Posting Dates:

五月 11, 2026 - 五月 24, 2026

Caterpillar is an Equal Opportunity Employer. Qualified applicants of any age are encouraged to apply

Not ready to apply? Join our Talent Community.