Computer Vision Engineer (AI Perception)

ROZOR; Hamilton; On-site; CAD 90,000 - 130,000; Full time

Job summary

ROZOR in Hamilton, ON is hiring a Computer Vision Engineer (AI Perception) to design perception systems that help our robots understand indoor environments.

You will develop CV and DL models, fuse camera and sensor data, and optimize real-time inference for embedded GPUs (Jetson). You will also integrate modules with ROS/ROS 2 and conduct field tests on ROZOR robots.

Qualifications

• Bachelor's/Master's in Computer Vision, AI, Robotics, or related field.
• 2+ years building computer vision / perception systems.
• Python proficiency and deep learning framework experience.
• Image processing and multi-view geometry knowledge.
• Experience with detection / segmentation models (YOLO, Mask R-CNN, DeepLab, DETR).
• ROS / ROS 2 and OpenCV familiarity.
• Real-time inference optimization ability.

Responsibilities

• Develop computer vision and deep learning models for object detection, tracking, segmentation, depth estimation, scene reconstruction, and mapping.
• Implement multi-modal fusion between camera, LiDAR, depth sensors, and IMUs.
• Build real-time perception pipelines optimized for embedded GPUs (Jetson).
• Analyze sensor data and improve robustness in real-world conditions.
• Integrate perception modules with ROS / ROS 2.
• Conduct field testing on ROZOR robots.
• Collaborate with autonomy, embedded, and hardware teams.
• Maintain datasets, labeling workflows, and model training infrastructure.

Skills

Python

Deep learning

Image processing

Multi-view geometry

Object detection

Segmentation

Depth estimation

Scene reconstruction

Mapping

Sensor fusion

ROS/ROS 2

OpenCV

Real-time inference optimization

YOLO

Mask R-CNN

DETR

Jetson

Education

Bachelor's/Master's in Computer Vision, AI, Robotics, or related field

Tools

ROS/ROS 2

OpenCV

Jetson

YOLO

Mask R-CNN

DETR

Job description

Hamilton, ON · Canada Full Time AI team

We are seeking a Computer Vision Engineer (AI Perception) to design and implement perception systems that enable ROZOR robots to understand complex indoor environments.

Responsibilities

• Develop computer vision and deep learning models for object detection, tracking, segmentation, depth estimation, scene reconstruction, and mapping.
• Implement multi-modal fusion between camera, LiDAR, depth sensors, and IMUs.
• Build real-time perception pipelines optimized for embedded GPUs (Jetson).
• Analyze sensor data and improve robustness in real-world conditions.
• Integrate perception modules with ROS / ROS 2.
• Conduct field testing on ROZOR robots.
• Collaborate with autonomy, embedded, and hardware teams.
• Maintain datasets, labeling workflows, and model training infrastructure.

What you bring

• Bachelor's/Master's in Computer Vision, AI, Robotics, or related field.
• 2+ years building computer vision / perception systems.
• Python proficiency and deep learning framework experience.
• Image processing and multi-view geometry knowledge.
• Experience with detection / segmentation models (YOLO, Mask R-CNN, DeepLab, DETR).
• ROS / ROS 2 and OpenCV familiarity.
• Real-time inference optimization ability.