Description
Join an innovative AI team to design, develop, and improve computer vision and image-processing pipelines, building solutions for video analysis, video understanding, and real-time visual processing. This role involves developing multimodal AI systems, working with various computer vision techniques like object detection and image segmentation, implementing and tuning Vision-Language Models, integrating large language models, optimizing and deploying machine learning models, translating research into product features, building APIs, collaborating with cross-functional teams, monitoring model performance, and maintaining clean code.
