Hadoop Admin - perm

E
* Pro Consulting service offerings include contingent Staff Augmentation of IT professionals, Permanent Recruiting and Temp-to-Hire. In addition, our industry expertise and knowledge within financial services, Insurance, Telecom, Manufacturing, Technology, Media and Entertainment, Pharmaceutical, Health Care and service industries ensures our services are customized to meet specific needs. For more details please visit our website

We have been retained for providing recruiting assistance, for direct hires, by one of the world-leading information technology consulting, services, and business process outsourcing organization that envisioned and pioneered the adoption of the flexible global business practices that today enable companies to operate more efficiently and produce more value.

• 1) Experience in large scale Hadoop cluster management
• 2) Ability to balance and tune cluster nodes for performance
• 3) Excellent Linux administration skills and understanding of system performance areas (memory, swap, disk i/o, network i/o, etc.)
• 4) Demonstrated experience tuning large application systems - must know how to benchmark and stress test under the highest simulated traffic conditions
• 5) Hive and HBase familiarity
• 6) Excellent understanding of hardware and software mirroring
• 7) Uderstanding of line and rack level IO tuning
• 8) Must understand and have worked with tools like IOzone
• 9) Thorough understanding of satellite,spacewalk, jumpstarts and kickstart profiling
• 10)
  Understanding of JVM administration and crash trace analysis
• 11)
  Proper understanding of NFS setup and block optimization.
• 12)
  Must know about frame set and communication protocols between multiple ethernets
• 13)
  Knowledge of RAID and its setup
• 14)
  Understanding og various JAVA OPTS related to hadoop
• 15)
  Understanding of zookeeper and zkdump.
• 16)
  Nagios configuration and automation
• 17)
  Must know PHP fo ganglia context customization.
• 18)
  Understanding of FIFO, Fair scheduler and Capacity scheduler and their usage
• 19)
  Understanding of ACLs on hadoop side.
• 20)
  Must understand how to use LVM on MapRFS
• 21)
  Must thorougly understand RPC and commuication protocols between nodes on TT and JT daemons
• 22)
  Fair knowledge of Google's Protobuf
• 23)
  Fair understanding of Hbase and CMS GC collector.