Devops Engineer

  • Management and Support
  • Amsterdam

Stream HPC

We’re getting too much junk in our server-room. We have a problem with our network (a higher lag than we should have), have a need to centrally manage access to the servers, want to automatically mount a user-space when at any server, and would like to have a simple piece of software that records benchmark-data. Can you help out?

This is what we have:

  • Gitlab based setup for CI, projects and more.
  • Mixed 10G and 1G network.
  • Various different Linux servers. For both manual tests via ssh as automated tests via Docker.
  • Some embedded boards running Linux.
  • Some Windows servers for testing.
  • There should be a single MacOS-server for testing.
  • A Docker-server with 2% memory usage

We seek a Devops engineer who can handle the above.

  • Linux primary, Windows, Android and MacOS secondary
  • Knows scripting and programming to get the services to get us further
  • Who can make Win-Lin dual-booting work.
  • Can improve the network.
  • Can setup software to centrally maintain/manage the servers.

Yes, there is enough to do right now. By the way, we make high performance software for GPUs and small clusters.

Send your application to jobs@streamhpc.com

To apply for this job email your details to jobs@streamhpc.com.

Related Posts

default

Question: do we work with CUDA?

Answer: Yes, actually a lot!The company was built on OpenCL and we are still work with the language a lot - from embedded GPUs and FPGAs to high-end ...

screenshot-twitter

The 12 latest Twitter Poll Results of 2018

Via our Twitter channel we have various polls. Not always have we shared the full background of these polls, so we've taken the polls of the past half ...

default

We don’t work for the war-industry

Last week we emphasized that we don't work for the war-industry. We did talk to a national army some years ago, but even though the project never star ...

opencl-logo

OpenCL Basics: Running multiple kernels in OpenCL

This series "Basic concepts" is based on GPGPU-questions we get via email more than once, or when the question is not clearly explained in the books.  ...