Check that descriptions accurately reflect what actually happened in the video, including failures, drops, or slipped grips - flagging any instances where outcomes were inaccurately described or "smoothed over."
Responsible for the development of deep learning and operations research models and related intelligent systems for the supply chain and logistics of the global E-Commerce business.
Participate in the exploration and development of personalized AI search, with a focus on harness engineering, post-training optimization, and rubric-based automated evaluation, to build next-generation search experiences that better understand users, reason over intent, and make intelligent decisions.
Build AI-powered features into business applications — such as integrating LLM APIs, embedding AI assistants, or adding intelligent automation — to enhance existing Java, .NET Core, and TypeScript applications.
Contribute to the project's foundational knowledge by documenting the shared technical understanding and implementation details aligned with high-level business requirements and project goals.
Contribute to the project's foundational knowledge by documenting the shared technical understanding and implementation details aligned with high-level business requirements and project goals.
Construct multimodal semantic links across video-product, product-product, and video-video relationships to support trend understanding, product mining, AIGC generation, and content-commerce supply optimization.
Recognition and rewards for excellence: We grow together with exceptional people — and it’s never too late to join. We’ve enhanced our reward system to recognize high performance, offering more opportunities for outstanding individuals to take on key projects and fully unleash their potential.
Design and execute persona/role-playing evaluation frameworks, covering metrics such as identity recognition, role compatibility, multi-turn stability, and style consistency.