Robotics Vision & Mapping Engineer

Ndimensions; Boston, Northern (MA, KY); Hybrid; USD 130,000 - 190,000; Full time

Job summary

Ndimensions Labs is seeking a Robotics Perception Engineer to own the perception layer that links vision, language, and navigation for home robotics. The role sits between AI and navigation teams, working with real hardware in real homes, on a path toward robust, language-grounded perception.

The position emphasizes real-world experimentation, calibration, and deployment on embedded GPUs, with close collaboration across perception, mapping, and control teams in Boston, MA or Toronto, ON.

Qualifications

• Experience on physical robotic systems, not just simulation.
• Grounding text to pixels with vision-language models.
• Real-time inference on embedded GPUs.
• Deep calibration and geometry knowledge (intrinsics, stereo, extrinsics).
• Strong Python and C++, with ROS2 on real robots.

Responsibilities

• Close the loop between language and pixels: verify that the grasped object is the commanded one in data and live inference.
• Ground language in the scene, turning a text query and an RGB-D frame into a pick target or navigation goal.
• Transform 2D detections into a persistent, object-level semantic map usable by language queries.
• Classify dynamic vs static map elements so the robot trusts changing parts of the environment.
• Evaluate, optimize, and deploy detection/segmentation models with real-time constraints on embedded GPUs.
• Build vision-based quality checks on training data, pre-verify episodes, and redact faces/personal info.
• Own camera calibration and rectification across the robot, ensuring depth/localization accuracy.

Skills

Python

C++

ROS2

Vision-language models

Grounding text to pixels

Embedded hardware

Education

Master's or PhD in Computer Vision/Robotics/CS

Tools

ROS2

Job description

Ndimensions Labs is seeking a Robotics Perception Engineer to own the perception layer that links vision, language, and navigation for home robotics. The role sits between AI and navigation teams, working with real hardware in real homes, on a path toward robust, language-grounded perception.

The position emphasizes real-world experimentation, calibration, and deployment on embedded GPUs, with close collaboration across perception, mapping, and control teams in Boston, MA or Toronto, ON.