Senior Computer Vision Engineer

DIGITAL PLACE VISION PTE. LTD.; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

Digital Place Vision Pte. Ltd. in Singapore is seeking an experienced Computer Vision Engineer to lead development of visual algorithms for warehouse shelf scanning, barcode/QR recognition, and SKU counting on robotic platforms.

You will integrate cameras, calibrate sensors, optimize models for edge deployment on platforms like NVIDIA Jetson, and weave vision modules into ROS2, with testing in real retail warehouse environments.

Qualifications

• Bachelor’s degree or above in CS/AI/EE/Robotics.
• Proficiency in C++ and Python; Linux development.
• Strong OpenCV and camera calibration experience.
• Experience with ML/DL frameworks (PyTorch or TensorFlow).
• Familiarity with ROS/ROS2 and image transport.

Responsibilities

• Barcode/QR Code Recognition: Develop and optimize robust detection/decoding algorithms.
• Product Recognition & Precision Counting (ML/AI): Train/deploy models to identify, classify, count SKUs.
• Camera & Hardware Integration: Select/integrate industrial cameras, calibrate intrinsics/extrinsics.
• Edge Deployment: Compress/accelerate models for NVIDIA Jetson; ensure real-time performance.
• ROS2 System Integration: Integrate vision modules into ROS2 using C++/Python.
• Field Testing & Iteration: Test in real warehouse environments; improve recall/accuracy.

Skills

C++

Python

Linux development

ML/DL

Software engineering

Education

Bachelor's degree or higher

Tools

OpenCV

ROS2

TensorRT

ONNX

CUDA

cv_bridge

Job description

We area team of Visionaries on a mission to light up the retail world with intelligent AI. As we deploy our cutting‑edge "air-ground coordination" robotics platform (AMR and drone systems), we are seeking an exceptional Computer Vision Engineer to give our robots precise "visual insight."

In this role, you will lead the development of the visual algorithm systems used for warehouse shelf scanning. From driving camera hardware to precisely identifying barcodes/QR codes in complex, real‑world environments, to leveraging machine learning for automated product recognition and accurate counting—you will directly drive the commercialization of our core automated inventory products.

Responsibilities:

• Barcode/QR Code Recognition Systems: Develop and optimize highly robust detection and decoding algorithms for barcodes and QR codes. Solve challenges related to image blur and distortion caused by robot movement, varying lighting conditions, and diverse viewing angles.
• Product Recognition & Precision Counting(ML/AI): Train and deploy machine learning/deep learning models (e.g., object detection models) to accurately identify, classify, and count various products (SKU counting) on warehouse shelves.
• Camera & Hardware Integration: Take charge of the selection and integration of industrial cameras / RGB-D cameras. Master camera intrinsic/extrinsic calibration, exposure/white balance control, and overall image quality tuning.
• Edge Model Deployment: Optimize, compress, and accelerate highly accurate AI models for efficient deployment on robotic edge computing platforms (e.g., NVIDIA Jetson). Ensure real‑time performance and high frame rates.
• ROS2 System Integration: Use C++ and Python to deeply integrate visual algorithm modules(nodes) into the robot's ROS2 architecture, enabling efficient interaction between visual data and the robot's navigation/control systems.
• Field Testing & Iteration: Conduct extensive testing in real retail warehouse environments. Analyze edge cases, continuously iterate, and improve the recall and accuracy rates of the vision system.

Requirements:

• Education: Bachelor’s degree or above in Computer Science, Artificial Intelligence, Electrical Engineering, Robotics, or a related field.
• Core Programming Skills: Solid programming foundation with proficiency in C++ and Python. Familiarity with Linux development environments and strong software engineering practices.
• Traditional Vision & Camera Tech: Strong mastery of OpenCV and a deep understanding of fundamental image processing algorithms. Proven hands‑on experience with camera calibration, multi-camera synchronization, and handling complex lighting/motion blur.
• Machine Learning/Deep Learning (ML/DL)Expertise:
• Proficiency in mainstream deep learning frameworks (e.g., PyTorch or TensorFlow).
• Familiarity with classic and cutting‑edge object detection algorithms (e.g., YOLO series, Faster R‑CNN) or image segmentation algorithms. Successful project experience using these models for object recognition and counting.
• Edge Deployment Experience: Familiarity with AI model edge deployment and inference acceleration tools such as TensorRT, ONNX, CUDA, or OpenVINO. Knowing how to extract maximum performance from compute‑constrained devices is crucial.
• Robotics Middleware: Familiarity with ROS / ROS2, understanding node communication, and image transport mechanisms (e.g., image_transport, cv_bridge).
• Bonus Skills: Experience using professional barcode decoding libraries (e.g., ZBar, ZXing,Halcon). Background in developing CV systems for the retail inventory or warehousing/logistics industries.