OVERVIEW
VinRobotics is hiring Senior Computer Vision & Visual SLAM Engineers for our Perception Team. You will own and deploy real-time perception systems that enable humanoids to see, localize, understand, and navigate complex environmentspowering manipulation, obstacle avoidance, semantic mapping, SLAM, and navigation.
RESPONSIBILITIES
- 6-DoF Pose Estimation (Manipulation): Design and deploy end-to-end 6D object pose pipelines using RGB/RGB-D/stereo. Make it robust to occlusion, clutter, symmetry, motion blur, and domain shift, and output confidence/quality object poses for grasp planning and manipulation execution.
- Stereo Depth Estimation: Build and optimize stereo depth. Handle low texture, reflective/transparent surfaces, lighting variation, and evaluate with metrics for accuracy, completeness, temporal stability, and latency.
- Semantic Perception & Mapping: Train segmentation models for traversability, obstacle classes, scene understanding (floor/walls/objects/humans/dynamic agents). Contribute semantic layers to 3D mapping / semantic SLAM and provide usable outputs to navigation.
- Visual / Visual-Inertial SLAM: Improve real-time SLAM/VIO for humanoid localization and mapping, including loop closure, place recognition, relocalization, and fusion of stereo/RGB-D/IMU for robustness in long-term operation.
- Deployment & Performance: Optimize on-robot runtime via profiling, CUDA, TensorRT/ONNX optimization, and efficient memory/dataflow (e.g., zero-copy where possible). Establish performance budgets and continuously improve reliability in real environments.
- Senior Ownership: Drive architecture decisions, roadmap execution, code/design reviews, and mentor engineers to raise overall system quality.
REQUIREMENTS
- Bachelor's or Master's degree in Computer Vision, Robotics, AI, or a related field (or equivalent experience) and 5+ years of hands-on experience.
- Strong CV/robotics fundamentals: multi-view geometry, camera models, calibration
- Solid C++/Python on Linux
- Deep learning + deployment: PyTorch/TensorFlow, ONNX/TensorRT, CUDA
- 3D processing: Open3D/PCL
- Robotics stack: ROS 2, experience with RealSense/ZED cameras, familiarity with MoveIt/Nav2
- SLAM/VIO, semantic mapping, grasp perception, sim2real/domain adaptation, GPU optimization, distributed training
WHAT WE OFFER
- Work on cutting-edge humanoid and autonomous robotics systems
- Real-world deployment on state-of-the-art robotic hardware
- Collaborative environment with AI researchers, roboticists, and system engineers
- Access to GPU clusters, simulation environments, and large-scale datasets
- Competitive compensation, benefits, and career growth opportunities
**We will proactively contact candidates who align well with the position's requirements.**
