Edge AI & Computer Vision Intern

免费注册后解锁"你的匹配分 vs 高分画像"与个人技能缺口。

We are investigating real-time edge computing architectures to enhance visual feedback in next-generation medical robotics. Our systems combine high-bandwidth video streams with real-time robotic telemetry to support precision tasks.
In this internship, you will lead the hands-on prototyping of an edge AI processing unit using a state-of-the-art Edge AI development platform. You will be responsible for bringing up the hardware from scratch, establishing a low-latency video pass-through pipeline, and evaluating how computer vision and machine learning models can extract insights and render helpful visual cues in real time.
Tasks :
• Hardware Bring-Up: Set up, configure, and benchmark a new edge AI development platform (operating system, drivers, hardware acceleration libraries, and high-speed video capture interfaces).
• Low-Latency Video Pipeline: Explore and prototype low-latency video streaming architectures using real-time processing frameworks to capture high-resolution camera feeds and drive responsive external displays.
• Telemetry & Visual Overlays: Ingest robotic telemetry alongside the video feed to render dynamic graphical annotations and spatial guidance cues directly onto the live stream.
• Computer Vision & AI Prototyping: Benchmark lightweight computer vision algorithms and modern neural network architectures (e.g., for object tracking, state awareness, or semantic scene understanding) on edge hardware.
• System Profiling & Documentation: Measure end-to-end processing delays, evaluate hardware resource utilization, and document the architecture to guide future product development.
Requirements
Required abilities :
• Enrolled in a Master’s degree or final year of a Bachelor’s program in Computer Science, Robotics, Embedded Systems, Electrical Engineering, or a related discipline .
• Practical programming experience in Python or C++.
• Working knowledge of Linux environments, shell scripting, and version control (Git).
• Foundational understanding of computer vision or machine learning using standard libraries (such as OpenCV, PyTorch, or ONNX Runtime).
• An exploratory, hands-on mindset with an interest in hardware bring-up, lab prototyping, and embedded development.
• Open-minded, self-driven & creative problem solving
• Fluency in English is a must
Beneficial Experience :
• Familiarity with real-time streaming SDKs (e.g., NVIDIA Holoscan, DeepStream, or GStreamer) or GPU acceleration tools (CUDA, TensorRT).
• Basic understanding of sensor fusion or 2D/3D coordinate transformations.
Benefits
What we offer :
A dynamic, innovative environment with cutting-edge medical technology that is shaping the future of robotic surgery.
Fast-growing Company where innovation meets agility.
Structured onboarding program and training, ensuring a confident start.
High degree of autonomy and flexibility.
Find more English Speaking Jobs in Switzerland on Arbeitnow

我们正在研究实时边缘计算架构，以增强下一代医疗机器人的视觉反馈。我们的系统结合了高带宽视频流和实时机器人遥测数据，以支持精确任务。
在这个实习中，你将领导使用最先进的边缘AI开发平台进行边缘AI处理单元的动手原型设计。你将负责从头开始搭建硬件，建立低延迟视频传输管道，并评估计算机视觉和机器学习模型如何实时提取见解并呈现有用的视觉提示。
任务：
• 硬件启动：设置、配置和基准测试新的边缘AI开发平台（操作系统、驱动程序、硬件加速库和高速视频捕获接口）。
• 低延迟视频管道：探索和原型设计使用实时处理框架的低延迟视频流架构，以捕获高分辨率摄像头信号并驱动响应式外部显示屏。
• 遥测与视觉叠加：将机器人遥测数据与视频流一起摄入，以便在实时流中直接渲染动态图形注释和空间引导提示。
• 计算机视觉与AI原型设计：在边缘硬件上基准测试轻量级计算机视觉算法和现代神经网络架构（例如，用于对象跟踪、状态感知或语义场景理解）。
• 系统分析及文档：测量端到端处理延迟，评估硬件资源利用率，并记录架构以指导未来的产品开发。
要求
所需能力：
• 在计算机科学、机器人技术、嵌入式系统、电气工程或相关学科攻读硕士学位或本科最后一年。
• Python或C++的实际编程经验。
• 熟悉Linux环境、shell脚本和版本控制（Git）。
• 对计算机视觉或机器学习（如OpenCV、PyTorch或ONNX Runtime）的标准库有基础了解。
• 具有探索性、动手能力和对硬件启动、实验室原型设计和嵌入式开发的兴趣。
• 开放心态、积极主动和创造性解决问题的能力
• 英语流利是必须的
有益经验：
• 熟悉实时流SDK（例如，NVIDIA Holoscan、DeepStream或GStreamer）或GPU加速工具（CUDA、TensorRT）。
• 对传感器融合或2D/3D坐标变换有基本了解。
福利
我们提供：
一个充满活力、创新的氛围，拥有领先的医疗技术，正在塑造机器人手术的未来。
创新与敏捷性相结合的快速发展公司。
结构化的入职计划和培训，确保自信的起步。
高度自主性和灵活性。
在Arbeitnow上找到更多瑞士的英语工作。

⚑ 岗位信息收录自公开招聘页（公开招聘平台），以雇主官网为准