Machine Learning Engineer - Computer Vision & Perception

About the role

The ASUS Robotics & AI Center is looking for a Machine Learning Engineer to join its global R&D team. The role focuses on designing, implementing and optimizing computer vision and perception systems for next-generation autonomous platforms. It suits a hands-on engineer with a strong foundation in computer vision and deep learning, experience deploying models in production, who enjoys working in a multidisciplinary environment.

Key responsibilities

• Develop and deploy machine learning models for computer vision and object recognition tasks.
• Optimize models for real-time performance on embedded and edge computing platforms.
• Build and maintain perception pipelines integrating data from cameras and other sensors.
• Evaluate and implement state-of-the-art techniques in deep learning, object detection and visual tracking.
• Design and run experiments, including simulation and real-world field testing, to validate model performance.
• Maintain and improve datasets, pipelines and tools to support efficient model training and deployment.
• Collaborate with robotics, systems and software engineers to deliver production-ready solutions.

Required profile

• Bachelor's degree or higher in computer science, electrical engineering, robotics or a related field.
• 5+ years of experience developing and deploying machine learning models for computer vision or perception applications.
• Strong problem-solving skills and ability to work in a collaborative, multidisciplinary team.
• Understanding of software development best practices, including coding standards, code reviews, source control and test automation.
• Experience with robotics, autonomous systems or real-time perception is a plus.

Required skills

• Proficiency in Python and deep learning frameworks such as PyTorch and/or JAX.
• Familiarity with classical computer vision techniques such as OpenCV.
• Plus: knowledge of MLOps practices (model versioning, CI/CD for ML).
• Plus: experience with camera geometry, 3D reconstruction or GPU programming (CUDA, Triton).