Computer Vision Engineer (Robotics)

Location: Watertown, MA, United States; on-site

Company

hirify.global builds AI robotics systems and deploys them in real-world facilities, combining research with physical robot operations.

What you will do

• Define technical approaches and success criteria for ambiguous perception problems in robot manipulation.
• Build and integrate detection, segmentation, tracking, object pose estimation, and 3D scene-understanding capabilities.
• Own camera calibration, coordinate transforms, synchronization assumptions, and sensor-quality checks.
• Create reproducible datasets and evaluations covering changes in objects, lighting, viewpoints, and occlusion.
• Select and adapt geometric methods and learned models based on accuracy, latency, robustness, and operational constraints.
• Deploy and maintain perception in the robot stack, diagnose failures through recorded data and physical experiments, and improve shared evaluation tools and documentation.

Requirements

• Independent ownership of a substantial computer-vision system from an ambiguous problem through tested integration.
• Strong Python engineering skills, including maintainable code, tests, and reproducible experiments.
• Practical command of camera models, calibration, coordinate frames, and 3D geometry.
• Experience with geometric vision or learned visual models and the ability to select the appropriate approach.
• Ability to build representative evaluations, isolate failure modes, and distinguish model improvements from data or measurement artifacts.
• Ability to communicate technical tradeoffs and resolve interfaces with research, software, mechanical, and electrical engineers.

Nice to have

• Perception deployed on physical robots, especially manipulation systems.
• Multi-camera or depth systems, sensor fusion, SLAM, or object pose estimation.
• OpenCV, Open3D, PCL, a modern deep-learning framework, C++, or GPU optimization.

Culture & Benefits

• Technical excellence, collaboration, respect, and clear ownership are valued.
• Engineering work follows a build, test, and learn cycle on physical robots.
• Success is measured through reproducible evaluations, documented sensing assumptions, physical-robot performance, and runtime constraints.
• Engineers contribute to design reviews, documentation, failure analysis, and mentoring.
• R&D roles are flexible and may evolve as team priorities change; level is determined through the interview process.