Senior Computer Vision Engineer

Asus•Boston, MA

1d•Hybrid

About The Position

The ASUS Robotics & AI Center is seeking a Senior Computer Vision Engineer to join our global research and development team. This role focuses on building the perception systems that allow our UAVs and other autonomous platforms to understand and operate in complex, real-world environments. We are looking for a hands-on engineer with practical experience taking computer vision algorithms from prototype to production, a strong foundation in 3D geometry and multi-sensor data, and a passion for making the math, the algorithms, and the code work together on real hardware. The ideal candidate thrives at the intersection of computer vision, robotics, and embedded systems, and is motivated by the challenge of delivering robust perception under the constraints of real-world autonomy.

Requirements

Familiarity with classical computer vision techniques and libraries (e.g., OpenCV) and with multi-sensor data integration (e.g., cameras, IMU, GPS/GNSS, LiDAR).
Strong fundamentals in linear algebra, probabilistic inference, and 3D geometry.
Proficiency in C++ and Python, with a commitment to writing clean, well-architected code.
Understanding of software development best practices, including coding standards, code reviews, design patterns, source control management, and test automation.
Bachelor's degree or higher in computer science, electrical engineering, robotics, or a related field.
5+ years of industry experience developing and deploying computer vision or perception software.
Hands-on experience with one or more of: visual odometry, SLAM, structure from motion, multi-view geometry, or 3D reconstruction.
Practical experience with object detection, tracking, or segmentation, including training and deploying deep learning models using frameworks such as PyTorch or TensorFlow.
Excellent written and verbal communication skills.
Ability to work confidently in a rapidly changing, fast-paced and results-oriented corporate environment where a high degree of flexibility is required.

Nice To Haves

Experience deploying perception software on embedded or edge compute platforms (e.g., NVIDIA Jetson) is strongly preferred.
Experience with robotics, autonomous systems, or real-time perception applications is a plus.
Familiarity with GPU/CUDA programming for accelerated vision processing is a plus.
Flexibility to attend virtual meetings with the Taiwan-based team at least three nights per week.

Responsibilities

Design, implement, and optimize computer vision algorithms for object detection, tracking, and visual recognition on UAVs and other autonomous platforms.
Develop 3D perception capabilities, including visual odometry, depth estimation, structure from motion, and SLAM, to support real-time mapping and navigation.
Build sensor fusion pipelines that integrate data from cameras, IMUs, GPS/GNSS, and other onboard sensors to produce accurate, low-latency situational awareness.
Optimize algorithms for deployment on resource-constrained edge and embedded compute platforms.
Characterize and quantify the performance of perception components through simulation, lab testing, and real-world field testing.
Collaborate with robotics, software, and hardware teams to integrate perception components into the broader autonomy stack.
Write clean, maintainable, and well-documented source code adhering to modern software development practices.
Work in a cross-functional team that takes ownership of the full software lifecycle.