About the TeamDedup team drives research and develops cutting-edge AI technologies that power core product experiences. Our work focuses on building large-scale, high-performance systems that support key strategies such as video deduplication, originality recognition, copyright detection, content safety, and content moderation. We are committed to delivering a seamless and safe user experience by pushing the boundaries of AI in production environments. Responsibilities 1. Build and scale the Dedup and Copyright system that supports billions of users globally 2. Design and deploy machine learning models to support video understanding and content integrity 3. Integrate cutting-edge AI technologies to improve model accuracy, performance, and system efficiency 4. Develop scalable data pipelines and infrastructure to support training and serving of ML models on real-time, unstructured data 5. Run experiments to evaluate and debug models in production environments 6. Collaborate with cross-functional teams to ensure smooth deployment and monitoring of ML systems

Minimum Qualifications 1. Bachelor's degree or above in Computer Science or a related field 2. Minimum of 1 year of industry experience in Machine Learning 3. Proficiency with at least one deep learning framework (., PyTorch, TensorFlow) 4. Experience in Multimedia or Computer Vision areas such as image/video/audio retrieval, representation learning, re-identification, or unsupervised/self-supervised learning Preferred Qualifications 1. Master’s degree or higher in Computer Science or a related field 2. Experience working in large-scale production environments or high-growth tech companies