Follow up on cutting-edge technologies such as global large model inference, GPU high-performance computing, distributed parallelism, and cache optimization, benchmark against mainstream inference frameworks such as vLLM and TensorRT-LLM, complete the implementation of solutions and technological innovation, continuously iterate and optimize the performance and cost advantages of the inference system, and build the core technological barriers of the team.
Participate in intelligent traffic management and large-scale platform development, with exposure to systems managing millions of machines and handling high concurrency. Improve code quality and system reliability through code review, automated testing, observability, and performance optimization.
Participate in building a large-scale graph storage and graph learning platform to improve relationship building and governance within the e-commerce community.
Problem Solving for Governance Applications: Address challenges such as long text/sequence modeling, few-shot learning, content moderation, violation detection, and policy recommendation using large models and multimodal approaches.
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.
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.
For inference track, develop the Volcano Ark MaaS (Model-as-a-Service) inference platform, optimizing the performance, cost efficiency, and reliability of large language model inference across hyperscale heterogeneous GPU clusters.
For inference track, develop the Volcano Ark MaaS (Model-as-a-Service) inference platform, optimizing the performance, cost efficiency, and reliability of large language model inference across hyperscale heterogeneous GPU clusters.
For inference track, develop the Volcano Ark MaaS (Model-as-a-Service) inference platform, optimizing the performance, cost efficiency, and reliability of large language model inference across hyperscale heterogeneous GPU clusters.