GPU Architect (GPU架构师)
英伟达半导体(深圳)有限公司
- 公司行业:电子技术/半导体/集成电路
职位信息
- 发布日期:2012-08-29
- 工作地点:上海
- 招聘人数:10
- 工作经验:应届毕业生
- 学历要求:本科
- 语言要求:英语熟练
- 职位类别:系统架构设计师
职位描述
Responsibilities:
- We are looking for world class engineers to design, model, analyze and verify next generations of GPU architecture.
- The candidates will work with a group of architects to design and develop proprietary internal tools for the visualization, analysis, and debug and verification of tests and applications on various functional and performance simulations of future chips.
- The candidates will have opportunities to get involved in cutting-edge GPU macro- and micro-architecture design, verification and optimization, including porting commercial applications to test benches, identifying performance hotspots and data mining for performance analysis.
REQUIREMENTS:
- Bachelor’s Degree or higher majoring in CS/EE/Mathematics or relevant fields.
- Strong C/C++ programming ability. Scripting language (Perl, Python, Ruby) experience is a plus.
- Strong problem solving capability, analytical and communication skills.
- Proactive, creative and a team player.
- Excellent English writing for engineering documentation, English oral well enough to attend meetings.
- Experience in the following areas is a plus:
- Microprocessor architecture design & verification.
- 3D graphics (D3D or OpenGL) application development.
- Multimedia (video, image processing, visualization) application development
- System level programming experience in OS, compiler, driver, tools, virtual memory system, etc.
- Parallel computing/CUDA/OpenCL/HPC development.
工作职责:
- NVIDIA需要世界级的工程师与我们一起对未来的GPU体系结构进行设计,分析,建模与验证。
- 应聘者将与一组架构师一起,设计和开发自有知识产权的工具,用于分析、验证和调试GPU芯片的功能与性能。
- 应聘者将有机会参与世界领先的GPU设计、验证与优化工作,包括将商用程序移植为测试用例,分析系统的性能热点以及为性能分析进行数据挖掘等。
招聘要求:
- 本科以上学历,计算机/电子/数学或相关专业。
- 较强的C/C++编程能力。熟悉脚本语言(Perl, Python, Ruby)尤佳。
- 思维条理清楚,解决问题能力强,善于沟通。
- 积极主动,具有创造力和团队精神。
- 英文听说读写出色,可以用英文撰写技术文档和参加会议。
- 具备下列领域相关经验者尤佳:
- 微处理器体系结构设计或验证
- 3D图形软件开发(D3D或OpenGL)
- 多媒体软件开发(视频,图像处理,数据可视化)
- 系统级编程经验(操作系统,编译器,驱动程序,除错工具,虚拟内存系统等)
- 并行计算/CUDA/OpenCL/HPC开发