AMD Radeon Instinct GPU组和EPYC Server CPU组长期内推和直招，仅限德州Austin

简历已发，谢谢楼主！zli**@andrew.cmu.edu

已發信件給您了，email: chi***u@gmail.com。再請您協助了，感謝！

感谢楼主，上次回错楼了，真是抱歉。

非常感谢楼主近日的帮助。谢谢

杜对赌对嘟嘟 发表于 2021-6-19 05:22
感谢楼主的信息分享！gd*** 已发邮件～祝好！

内部推荐邮件已发送，请查收

感谢楼主的信息分享！gd***b@gmail.com 已发邮件～祝好！

最近AMD DCGPU硬件组和MLSE软件组均有很多职位放出，但一般标注MTS、SMTS、PMTS的不接受应届毕业生，请留意。

Machine Learning Performance Engineer.- 100521
Location: Austin, Texas, US

The Role:
. 1point3acres.com This is a highly visible position with the opportunity to work closely with teams across AMD and impact MLPerf optimizations on AMD hardware and software architectures.

The Person:
We are seeking a machine learning specialist with a background in frameworks such as PyTorch/TensorFlow, and machine learning workloads. The successful candidate will have a passion for machine learning algorithms and understand the mapping of the workloads (such as CNNs, Transformer, BERT, recommendation models) on CPU/GPU architecture.

Preferred Experience:
Expertise with PyTorch/TensorFlow and performance tools such as nvprof and rocprof.
Experience with standard machine learning models such as ResNet50, Transformer, SSD, BERT, DLRM and Reinforcement Learning
Familiarity with large scale execution of machine learning models on clusters connected with Ethernet/InfiniBand

Accelerated Computing Network Engineer- 99256
Location: Austin, Texas, US

THE ROLE:
Do you want to be a key contributor to highly-scaled HPC and ML training clusters from AMD?  The Network Validation and Performance team is looking for computer networking engineers to ensure GPUs perform optimally across high performance networks.  You will be validating different networking technologies and identifying performance optimizations in areas such as: platform configurations, BIOS settings, network configurations, OS settings, GPU architecture, etc.  You will be interfacing with networking partners as well as senior hardware and software engineers and architects in a very flat AMD organizational structure.  You will be exposed to cutting edge technology and will have the opportunity to build out the test environment and contribute to test plans and methodology.

PREFERRED EXPERIENCE:
Comfortable setting up servers, changing hardware, updating firmware and installing server software
RDMA network and PCIe configuration and troubleshooting
Industry standard performance benchmarks
System and software performance debug tools
ML and/or HPC system design

如果有明顯跟職位要求不符的同學，請在jobs.AMD.com上找好符合的在Texas的其他職位，我也可以幫忙內推

AMD Datacenter GPU Machine Learning Software Engineering大组新职位放出，地点还是Austin，工作内容与85225（Linux Kernel Developer）基本相同，但更偏重HPC的RAS/MCA/Reset子系统：https://jobs.amd.com/job/Austin-MTS-Software-System-Design-Eng_-Texa/748686300/
参考：https://www.kernel.org/doc/html/v4.14/admin-guide/ras.html
这是上千块GPU一同训练的大型机器学习系统的必备功能。

xqd 发表于 2021-5-22 19:14
邮件已发，感谢楼主！email: ch****

已经内部推荐，请查看邮件。