I. ABOUT VINDYNAMICS

At VinDynamics, we design safe, affordable, and intelligent humanoid robots to assist in everyday life — robots for everyone. Backed by Vingroup, Vietnam’s leading technology conglomerate, we are on a mission to make advanced robotics accessible, reliable, and beneficial for billions of people worldwide. By combining cutting-edge AI, world-class engineering, and human-centered design, we aim to seamlessly integrate robots into daily life — enhancing safety, productivity, and happiness at home and beyond.

II. OVERVIEW

• Position: Intern – Computer Vision

• Company: VinDynamics

• Division – Department: Application Deployment Division, AI Application Department

• Report to: Head of AI Application

• Location: Hanoi, Vietnam

Job summary:
The Computer Vision Engineer/ Intern will develop and deploy vision algorithms that enable humanoid robots to perceive and understand human behaviors in real-world environments. This role focuses on human pose estimation, action recognition, and visual perception to enhance natural human-robot interaction. You will collaborate with cross-functional AI teams to integrate these capabilities into intelligent, assistive humanoid systems.

III. REQUIREMENTS

Preferred qualifications of education and experience

• Bachelor degree in Computer Science, Artificial Intelligence, Computer Vision, Automation, or a related field.

• Proficiency in Python and C++, with experience using TensorFlow or PyTorch.

• Strong understanding of computer vision models such as CNNs, Transformer-based models (e.g., ViT, Swin Transformer).

• Hands-on experience with human pose estimation, keypoint detection, and behavior/action recognition.

• Experience with popular computer vision frameworks and libraries (OpenCV, Detectron2, MMDetection, YOLO, MMPose, OpenPose).

• Experience working with large-scale datasets (e.g., COCO, ImageNet, KITTI, Human3.6M, MPII, AVA) and video data processing.

• Knowledge of model optimization and deployment on embedded systems or edge devices (e.g., NVIDIA Jetson).

• Experience deploying vision-based AI solutions on hardware such as NVIDIA Jetson or Intel RealSense.

• Publications in top-tier AI/Computer Vision conferences (CVPR, ICCV, NeurIPS, ICRA).

• Experience developing computer vision solutions for robotics or autonomous vehicles.

Personality / Attitude

• Strong interpersonal and leadership skills

• Proactive, dedicated, business-oriented, responsible and willing to learn

• Good communication skills, creative problem-solving skills and attention to detail

IV. JOB DESCRIPTION

• Design, develop, and deploy computer vision algorithms for humanoid robots, including object detection, image segmentation, human pose estimation, action recognition, and object tracking.

• Build deep learning models to enhance robots' understanding of human motion and behavior with high accuracy and efficiency.

• Work with RGB cameras, depth sensors, and LiDAR to optimize robots’ perception capabilities in complex environments.

• Collaborate with cross-functional teams to integrate AI models into the overall robotic control system.

• Evaluate and optimize model performance in both simulation and real-world environments.