NVIDIA Compute Arch 是一个处于业界最前沿的团队，研究的范畴包括 GPU / HW Accelerator 相关的架构设计和应用优化（计算机视觉，深度学习、无人驾驶）。
欢迎有高性能计算、计算机体系结构背景，并具有一定编程能力和数据分析能力的同学加入。如果是相关专业的 PhD 那就更好啦！ 另外社招、应届、实习都可以。简历请直接发到我的邮箱 [email protected] 。
这次同时招以下三个方向：
High performance CUDA kernel development
Develop super-fast kernels for cuDNN and Tensor RT
Requirement
- CUDA programming and optimization
- Assembly level optimization with SSE, AVX, or other SIMD instructions
- Compiler
- General compute architect
Develop methodology and evaluate compute features for future architecture
Model deep learning performance for future architecture
Requirement
- Deep understanding of compute architecture in general
- Good programming skill
- DL algorithm
Analyze deep learning algorithms.
Study Computation/Memory complexity. Computation pattern etc …
Requirement
- Deep understanding of implementation of DL algorithms
- Good compute architecture in general
- Good programming skill
Select Language