Computer Vision Specialist (Robotics)

Hyphen Connect; Oregon (WI); On-site; USD 90,000 - 130,000; Full time

Job summary

Hyphen Connect is seeking a skilled Computer Vision Engineer to advance robotic systems through high-fidelity spatial mapping and real-time object recognition. You will work closely with cutting-edge technology to integrate vision systems with robotic manipulation and navigation, enhancing automation capabilities. Key responsibilities include implementing mapping and recognition pipelines, integrating systems, and training Vision-Language-Action models. Ideal candidates will have proficiency in modern spatial AI techniques and experience with robotic hardware.

Qualifications

• Proficiency in 3D Gaussian Splatting, NeRFs, and modern SLAM algorithms.
• Experience with multimodal spatial AI frameworks.
• Previous work integrating computer vision outputs with ROS2 or robotic hardware.

Responsibilities

• Implement high-fidelity spatial mapping and real-time object recognition pipelines.
• Integrate vision systems directly with robotic manipulation and navigation controls.
• Train and fine-tune Vision-Language-Action (VLA) models.

Skills

3D Gaussian Splatting

NeRFs

modern SLAM algorithms

multimodal spatial AI frameworks

ROS2 integration

Job description

We are seeking a skilled Computer Vision Engineer. This role is pivotal in advancing robotic systems through high-fidelity spatial mapping and real-time object recognition. You will work closely with cutting-edge technology to integrate vision systems with robotic manipulation and navigation, to enhance automation capabilities.

Responsibilities

• Implement high-fidelity spatial mapping and real-time object recognition pipelines.
• Integrate vision systems directly with robotic manipulation and navigation controls.
• Train and fine-tune Vision-Language-Action (VLA) models.

Required Skills

• Proficiency in 3D Gaussian Splatting, NeRFs, and modern SLAM algorithms.
• Experience with multimodal spatial AI frameworks.
• Previous work integrating computer vision outputs with ROS2 or robotic hardware.