1. Address issues related to computational capacity limitations, communication delays, and the scalability of distributed systems, in accordance with business needs.
2. Collaborate with algorithm, hardware, and operations teams to develop efficient and stable computing infrastructure.
1. Solid foundation in computer architecture; familiarity with parallel computing and the design of data-intensive systems.
2. Strong mathematical skills, including linear algebra, numerical analysis, and optimization of algorithm complexity.
Preferred Qualifications/Additional Notes
1. Experience with inference frameworks such as TensorRT or Triton Inference Server is a plus.
2. In-depth understanding of TCP/IP and RDMA protocol stacks; familiarity with DPDK/SPDK development is also beneficial. Those with experience in optimizing networks within supercomputing centers or cloud computing environments are preferred.
3. Knowledge of the Transformer architecture and the main procedures involved in training large models.
As an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.