Role Summary

This Mid-Senior level Vision/AI Engineer will be responsible for the research, design, development, and deployment of advanced computer vision and artificial intelligence solutions across our diverse portfolio of robotic systems.

Core Responsibilities

• Algorithm Development: Design and implement robust, real-time computer vision algorithms for perception tasks such as object recognition, tracking, 3D reconstruction, and pose estimation.

• Model Training & Optimization: Develop, train, and fine-tune deep learning models (CNNs, Transformers, etc.) for specific robotic applications, including:

  • AMR (Autonomous Mobile Robots): Visual SLAM, semantic segmentation for navigation, and advanced obstacle detection.

  • Manipulators: Accurate 6D object pose estimation for complex pick-and-place and assembly operations.

  • AI Inspection: Defect detection, anomaly recognition, and quality assurance using high-resolution imagery.

• System Integration: Integrate vision and AI pipelines with the broader robotics ecosystem, utilizing frameworks like ROS/ROS2 and ensuring seamless communication with motion planning and control systems.

• Performance & Reliability: Optimize deployed models for high performance and low latency on embedded platforms (e.g., NVIDIA Jetson, industrial PCs) to meet real-time operational requirements.

• Collaboration: Work closely with the Solution Architect Lead to translate high-level requirements into scalable and maintainable AI system architectures.

Required Skill Set

• Experience: 4+ years of professional experience focused on Computer Vision and Deep Learning, preferably within a robotics or industrial automation context.

• Technical Proficiency:

• Expertise in Python and proficiency in C++ for performance-critical components.

• Fluency in major deep learning frameworks (PyTorch or TensorFlow).

• Strong background in OpenCV and image processing techniques.

• Demonstrable experience with sensor data, including RGB-D, LiDAR, and stereo vision.

• Robotics Knowledge:

  • Solid understanding of robotics concepts (Kinematics, Perception, Planning).

  • Hands-on experience with Robot Operating System (ROS) is highly desirable.

Nice to Have

• Experience developing vision systems for Humanoid or human-robot collaboration (HRC) platforms.

• Familiarity with containerization (Docker) and deployment strategies for edge devices.

• Experience with advanced techniques like Reinforcement Learning for robotics control.

Reporting Structure

This position reports directly to the Solution Architect Lead, ensuring that all computer vision and AI subsystems align seamlessly with the overarching software architecture and project roadmap. You will operate within a cross-functional R&D team, collaborating closely with navigation, control, and hardware engineers to integrate perception capabilities into AMR, manipulator, and humanoid platforms.