Senior Computer Vision Engineer

Key Responsibilities

• Research and implement multi-modal large models (image-text, image-audio, etc.) training, fine-tuning, and inference optimization strategies, continuously improving model performance, efficiency, and generalization ability.
• Design and optimize computer vision models and algorithms (e.g., detection, classification, segmentation, feature extraction) to support real-world applications.
• Collaborate with cross-functional teams (product, engineering, data) to translate research into scalable, reliable, and production-ready solutions.
• Use C++ to implement and optimize models and systems, including deployment, performance tuning, and integration, ensuring low latency and high throughput.
• Stay up to date with advances in computer vision and multi-modal AI, and apply new methods to improve model performance and product impact.
• Contribute to technical discussions, code reviews, and knowledge sharing to improve code quality and engineering best practices.

Minimum Qualifications

• Master’s or Ph.D. in Computer Science or a related field, with strong expertise in computer vision and machine learning.
• 1-3 years of experience in multi-modal large model training, fine-tuning, and optimization (e.g., CLIP, Flamingo, BLIP, or self-developed multi-modal models), with a deep understanding of multi-modal fusion mechanisms.
• Strong foundation in computer vision, including object detection, image classification, feature matching, and image enhancement.
• Strong C++ development skills, with proficiency in STL, multi-threading, memory management, and performance optimization; experience in production-level implementation and deployment is required.
• Familiar with deep learning frameworks (e.g., PyTorch, TensorFlow) and computer vision libraries (e.g., OpenCV, OpenMMLab).
• Strong problem-solving ability, self-driven, and passionate about technological innovation; ability to work independently and in a team.

Preferred Qualifications

• Experience in edge device algorithm deployment, published papers in top computer vision conferences (CVPR, ICCV, ECCV), or open-source project contributions in related fields.

What do we provide:

• A fun, supportive and engaging environment.
• Opportunity to make a significant impact on the transportation revolution by the means of advancing autonomous driving.
• Opportunity to work on cutting edge technologies with the top talent in the field.
• Competitive compensation package.
• Snacks, lunches and fun activities.