Tumblr is one of the most heavily trafficked sites in the world. Your job is to help us handle that traffic. Our service runs on thousands of servers in our own data centers and up in the cloud. We are looking for systems and performance engineers to increase the throughput and utilization of our systems as well as decrease app latency and operational costs.

Candidates should, naturally, have an in-depth understanding of systems. Specifically:

  • They should know how to measure and optimize performance of the processor caches, buses and disks.

  • They should have a thorough understanding of linux system fundamentals, ranging from kernel configuration to troubleshooting code.

  • They should be able to manage issues arising from use of the IP stack, file system, memory management subsystem and other areas.

Additionally, the candidate must be a strong proponent of automation, in everything from system setup and configuration to the monitoring of applications, systems and networks.

Requirements

  • Understanding of the design of the Linux operating system.

  • Good understanding of layer-3 network protocols and technologies.

  • Solid understanding of TCP/IP networking.

  • Solid knowledge of Linux kernel debugging and performance analysis.

  • Good knowledge of concurrency and synchronization issues/techniques in a multiprocessor environment.

  • Knowledge of algorithms to design and deploy high availability infrastructure

  • In depth knowledge of system boot sequence.

  • Ability to code in Ruby and/or Python and/or Scala and/or C/C++.

  • Smarts, humility, and an equal willingness to learn and teach.

  • A sense of ownership, initiative, and drive.

  • A PhD or MS in computer science is preferred.
Apply for this Job
* Required

File   X
File   X





Share this job: