V2EX = way to explore
V2EX 是一个关于分享和探索的地方
现在注册
已注册用户请  登录
• 外包信息请发到 /go/outsourcing 节点。
• 不要把相同的信息发到不同的节点
madeye
V2EX  ›  酷工作

[上海] NVIDIA Computing Architecture 组招聘

  •  4
     
  •   madeye · 2016-12-02 15:27:32 +08:00 · 3965 次点击
    这是一个创建于 2894 天前的主题,其中的信息可能已经有所发展或是发生改变。
    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 架构设计和相关应用的优化(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]

    -------------- 以下为 JD -------------

    The NVIDIA GPU Computing Architecture group is looking for world class computer architects to join and lead our effort to advance the state of parallel computing. Our team is designing the fastest and most efficient parallel architectures from automotive to the world's fastest super computers.

    RESPONSIBILITIES (possible directions):
    • Enhance GPU architectures to extend the state of the art in performance, efficiency, programmability and reliability
    • Analyze, tune and prototype key applications for new GPU architectures
    • Build model to predict performance, power and reliability on future architecture
    • Design, and develop tools to analyze, simulate, validate, and verify application performance, and energy consumption
    • Collaborate across the company to guide the direction of GPU computing, working with software, research and product teams

    DESIRED SKILLS and EXPERIENCE:
    • MS Degree in relevant discipline (CS, EE, Math). PhD helpful
    • Strong programming skills in C or C++
    • Strong background in computer architecture, parallel processing, signal processing and/or high performance computing
    • Experience in characterizing and modeling system-level performance or power, executing comparison studies, and documenting and publishing results
    • Optional/Plus - Background in computer vision, machine learning, or any HPC domain
    • Optional/Plus - Strong programming skills in CUDA, Perl, OpenMP, MPI or Python
    第 1 条附言  ·  2017-03-22 13:30:17 +08:00

    继续招人啦,这次同时招下面三个方向:

    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. Computation/Memory complexity. Computation pattern etc…
    • Requirement
      • Deep understanding of implementation of DL algorithms
      • Good compute architecture in general
      • Good programming skill
    13 条回复    2017-03-22 13:31:17 +08:00
    unoyx
        1
    unoyx  
       2016-12-02 18:12:47 +08:00
    简历需要英文的?
    codingadog
        2
    codingadog  
       2016-12-02 18:17:36 +08:00 via iPhone
    膜拜 ss-libev 作者
    madeye
        3
    madeye  
    OP
       2016-12-02 23:01:26 +08:00 via Android
    @unoyx 随意的。
    ggaaooppeenngg
        4
    ggaaooppeenngg  
       2016-12-03 02:54:36 +08:00 via iPhone
    本科刚毕业的可以吗
    ggaaooppeenngg
        5
    ggaaooppeenngg  
       2016-12-03 02:55:03 +08:00 via iPhone
    z
    madeye
        6
    madeye  
    OP
       2016-12-03 07:34:15 +08:00 via Android
    @ggaaooppeenngg 这种比较难,不过可以先把简历发过来看看。
    hackpro
        7
    hackpro  
       2016-12-03 13:04:09 +08:00
    春招的时候投了一次 不过 HR 收了简历后没啥消息了
    madeye
        8
    madeye  
    OP
       2016-12-03 14:23:20 +08:00
    @hackpro 专业对口比较重要,需要硬件相关的背景。否则的话, HR 有可能会无视掉。。。
    wannafly
        9
    wannafly  
       2016-12-03 14:53:52 +08:00
    @madeye 干 EDA 的呢...
    madeye
        10
    madeye  
    OP
       2016-12-03 18:04:54 +08:00 via Android
    @wannafly 可以的
    isbase
        11
    isbase  
       2016-12-03 22:44:57 +08:00 via Android
    感谢大神的项目😀😀😀
    phx13ye
        12
    phx13ye  
       2016-12-05 09:46:12 +08:00
    膜拜 ss-Android 作者
    madeye
        13
    madeye  
    OP
       2017-03-22 13:31:17 +08:00   ❤️ 1
    继续招人啦,这次同时招下面三个方向:

    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. Computation/Memory complexity. Computation pattern etc …
    Requirement
    Deep understanding of implementation of DL algorithms
    Good compute architecture in general
    Good programming skill
    关于   ·   帮助文档   ·   博客   ·   API   ·   FAQ   ·   实用小工具   ·   5751 人在线   最高记录 6679   ·     Select Language
    创意工作者们的社区
    World is powered by solitude
    VERSION: 3.9.8.5 · 24ms · UTC 03:28 · PVG 11:28 · LAX 19:28 · JFK 22:28
    Developed with CodeLauncher
    ♥ Do have faith in what you're doing.