OpenNash Jobs
Tencent Holdings · Beijing

异构加速框架工程师(深圳/北京/上海)

Beijing

Listed on Tencent Holdings’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there.

Apply on Tencent Holdings’s careers site →

Job description

Responsibilities

  • 协同算法团队co-desgin,针对AI推理构建GPU/AI芯片底层性能优化与调优;
  • 机器学习框架层架构创新,核心模块优化和扩展,提升计算效率与资源利用率;
  • 深入分析GPU/AI芯片的硬件架构特性,设计并实现高性能算子、算法和特性使能组件;
  • 探索前沿技术方向(如混合专家模型MOE、动态计算图编译优化等)。 Requirements
  • 熟练掌握C/C++、Python编程语言,具备良好的coding和调试能力;
  • 熟悉GPU/AI芯片编程,如CUDA,Triton,Ascend C等;
  • 熟悉Cublas,Cutlass,CK等高性能算子开发工具;
  • 熟悉Torch-Compile等AI编译模块者优先;
  • 熟悉主流开源模型或推荐模型,有实际性能调优经验(如KV Cache优化、动态批处理、Attention算子定制等);
  • 扎实的高性能计算基础,熟悉并行计算、内存优化、通信优化等技术;

加分项

  • ;
  • AI数据、搜广推等场景架构和加速经验;
  • 相关领域开源项目贡献、顶会论文等。

More jobs at Tencent Holdings

OpenNash lists jobs from employers’ own careers sites and does not handle applications. Dates come from the employer where stated; “first seen” and “last checked” are our own observations.