Linux System Engineer (Supercomputer)
New York City, Ny, Us
Administrate 3000 Linux servers in a net booted environment and support Linux Farms and 400 way clusters. Create Linux Custer servers on Dell 1855 for Data Mining/Data Warehousing environments. This includes partitioning hard drives, creating swap space, formatting disk, creating ext2 file systems, install system packages, configure network interface card and IP if needed and add routing tables. Set up and configure services to startup upon boot such as: sendmail, NFS, SSHD, NTP, DHCP, FTP Rsync, Samba, gmond, Syslog-nd and Crond. Control load balanced and high availability environments using both Radware Load Balancing techniques along with in house concepts. Develop and support shell scripts to obtain optimum system performance and monitoring. Diagnose complex system and network problems using dumps, traces, or other diagnostics tools. Diagnose system performance problems as well as develop web based tools for NOC department to utilize system indicators for entire Linux server environment to troubleshoot, and diagnose application incidents as well as improve operations. Develop Linux based environment for in house applications and system components and aid in installation by end users. Develop methodologies based on best practice to optimize system configurations and installation of OS on cross platform hardware environment. Recommend and change system parameters or configuration variables to improve overall system performance. Review job control/scripts and assist in modifications of systems for optimum performance and operation.