Architectural CV Engineer - AI/ML for Structural Drawings

Genia; Singapore; On-site; SGD 20,000 - 31,000; Full time

Job summary

Genia in Singapore is seeking a motivated student to join its Computer Vision team on a hands-on internship. You will assist in developing and testing CV models for detecting elements in architectural drawings, apply classic CV techniques, and train deep learning models under senior engineers.

You will help with data prep for DWG preprocessing, rasterization, augmentation, and annotation; document experiments; collaborate to integrate models into the Structural AI Agent.

Qualifications

• Education background: Currently pursuing a Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Computer Vision, or a related field (preference for students from top-tier universities).
• Experience from courses, internships, or projects in computer vision, image processing, or machine learning is preferred.

Responsibilities

• Assist in developing and testing computer vision models for detecting and segmenting elements in architectural drawings.
• Apply and experiment with classic CV techniques (edge detection, contour analysis, shape recognition) on drawing data.
• Train and evaluate deep learning models (CNN, U-Net, YOLO, Mask R-CNN) under the guidance of senior engineers.
• Support the data preparation pipeline, including DWG preprocessing, rasterization, augmentation, and dataset annotation.
• Document experimental processes, benchmark results, and share insights with the team.
• Collaborate with engineers and researchers to integrate models into our Structural AI Agent.

Job description

Genia in Singapore is seeking a motivated student to join its Computer Vision team on a hands-on internship. You will assist in developing and testing CV models for detecting elements in architectural drawings, apply classic CV techniques, and train deep learning models under senior engineers.

You will help with data prep for DWG preprocessing, rasterization, augmentation, and annotation; document experiments; collaborate to integrate models into the Structural AI Agent.