Refine Reset All
Sort by
Location
Employer/Recruiter
Date Posted
Location
Job Type
Employer/Recruiter
All Filters

Trace Layout Jobs In China - 5 Job Positions Available

Top Cities:
1 – 5 of 5 jobs
Nvidia jobs

We are looking for a Senior Signal Integrity & PCB Quality Engineer! NVIDIA is powering the next wave of AI and accelerated computing, and our PCB technology is a critical enabler of the worlds highest-performance systems.

Nvidia  17 days ago
Sika AG jobs

Company Description Sika is a specialty chemicals company with a globally leading position in the development and production of systems and products for bonding, sealing, damping, reinforcing, and protection in the building sector and industrial manufacturing.

Sika AG  4 days ago
Lumentum jobs

Its fun to work in a company where people truly BELIEVE in what theyre doing! Were committed to bringing passion and customer focus to the business. If you like wild growth and working with happy, enthusiastic

Lumentum  5 days ago
Qualcomm jobs

Company: Qualcomm China Job Area:Engineering Group, Engineering Group Software Applications Engineering General Summary: Company Overview Qualcomm Technologies, Inc. is a world leader in wireless technology innovation and the driving force behind the development, launch, and expansion

Qualcomm  2 days ago
北京思朗科技有限责任公司 jobs

2027校招-算子开发工程师(上海/北京/成都) 上海、北京、成都 校招 正式 职位描述 岗位职责- 负责公司自研 AI 加速芯片上的 算子库设计与实现,覆盖训练与推理核心算子(如 GEMM/Conv/Attention/LayerNorm/Softmax/Reduce/Scatter-Gather 等)。- 基于芯片计算单元、片上存储(SRAM/Cache)、HBM 带宽、NoC 拓扑、DMA/异步拷贝能力,进行 算子性能建模与瓶颈分析(roofline、访存/计算比、流水并行),制定优化策略。- 设计并落地 kernel 调度与 tiling 策略:多级分块、数据布局(layout/packing)、向量化/张量化、双缓冲/多缓冲、算子融合(fusion)等。- 建设算子库工程化体系:算子接口规范、版本管理、性能回归、单测/对齐验证、精度与数值稳定性、跨平台兼容- 参与端到端模型性能优化:对接 PyTorch/TensorFlow/ONNX Runtime 等前端(或公司自研框架),完成算子覆盖、性能调优和线上问题定位(profiling/trace)。 职位要求 (优秀应届可放宽)。- 计算机/电子/自动化/数学等相关专业;- 熟悉深度学习常见算子与数值实现(GEMM/Conv/Attention/Norm/Reduce),理解训练/推理的差异(激活、梯度、混合精度、量化)。- 扎实的 C/C++ 能力,良好的工程习惯;能熟练使用性能分析工具(profiling、trace、perf、火焰图或自研工具)。- 熟悉至少一种加速器编程模型或并行体系(CUDA/OpenCL/ROCm/Metal/TVM/Triton/oneDNN/CUTLASS 等)并能迁移到自研 ISA/Runtime。- 具备系统级性能意识:理解存储层次、带宽/延迟、cache/预取、NUMA、DMA、并行同步等,对算子优化有方法论。加分项- 有自研芯片/FPGA/NPU/GPU 上

北京思朗科技有限责任公司  1 day ago

Subscribe for job alerts and resources to make your job search easier!

Confirmation email sent to

Check your email and click on the link to start receiving your job alerts

Receive the latest job openings for:

trace layout

Confirmation email sent to

Check your email and click on the link to start receiving your job alerts

All Filters Apply
Sort by
Location
Employer/Recruiter