• 7 Years of High Performance Computing System administration experience
• Excellent knowledge in designing, prototyping and deploying HPC clusters
• Strong understanding of cluster resource managers, schedulers, clusterware and GPU computing
• Experience in benchmarking and performance optimization of large-scale HPC systems
• Experience in installing and managing high performance storage and network interconnects
• Managed a team 5 of system administrators
• Strong knowledge of Bio Informatics cluster software and Sequencing instruments
• Extensive experience in developing Linux installers for cluster software and OS deployment and automation
• Experience in creating PRD and RFP documents for projects and evaluating hardware from multiple vendors before purchasing
• Experience in building computer labs ground up, capacity planning and installing racks
• Experience in purchasing over 30 million dollars worth of equipment from various vendors for various projects, from specification, to negotiation, lease/purchase and delivery/installation on site
• Extensive experience in troubleshooting Linux OS, filesystems, cluster hardware, scripting and GPU computing hardware
• Ability to create, maintain, and implement scripts in order to reduce administrative efforts
• Ability to operate in a multi-platform, multi-operating system, multi-component environment utilizing a large number of server builds and configurations.
• Experienced in project management skills and the demonstrated ability to drive for results
• Excellent interpersonal, communication, customer interaction, documentation skills and decision-making ability

RHEL, SUSE, Debian, Ubuntu, PBS, LSF, SGE, MAUI, TORQUE, MOAB, ROCKS, SCYLD, Lustre, GPFS, NFS, DNS, NIS, LDAP, DHCP, MySQL, FTP, IPMI, SNMP, VMware, Apache and Tomcat Webservers, Postgres, kickstart, RPM building, OS Install images, shell and python scripting, RAID setup, High performance storage DDN, Xanadu, RAID inc , 10GigE network interconnects and switches ethernet and Infiniband Mellanox, CISCO, DELL DELL 10th,11th and 12th generation hardware, Nvidia Tesla, C2050, M2075, C410x, NextIO

• Tech lead for Next-gen DNA Sequencing instruments compute design and administration SOLiD 1,2,3,4 and SOLiD 5500
• Evaluated, prototyped, built and supported HPC clusters, servers and workstations for Next Gen DNA Sequencing instruments SOLiD, SOLiD 5500 and R D software development and V V teams.
• Provided leadership and mentored team of system administrators to support onsite compute hardware for R D software, V V and system validation teams, also supported field engineers.
• Developed and supported installers for cluster software BioScope, LifeScope to work on heterogeneous HPC clusters involving various operating systems - RHEL, SUSE, Debian and resource managers/schedulers PBS, LSF, SGE, MAUI. Supported it on over 100 different clusters at remote sites ranging from 10-node to 500-node clusters.
• Provided continued Linux and systems administration support for R D software development, V V, Systems Integration teams and field engineers.
• Managed and provided system administration support to Genome Sequencing center consisting of 20 SOLiD 5500 instruments
• Worked with DELL and Nvidia to address hardware issues and developed diagnostic suite for field engineers
• Built and supported numerous clusters for R D teams including high performance storage and interconnects Dell PE Blade Servers, C410x, DDN GPFS storage, Xanadu lustre, Mellanox 10GigE
• Maintained custom kickstart and YUM repositories for automated and network-based system and software installations on a fleet of Linux based clusters, workstations and servers
• Developed python and bash scripts for monitoring system resources to assist with system performance tuning, automate data backups and inventory the systems on the network.
• Documented as-built installations, configurations, end-to-end system setup procedures, SOP and troubleshooting guidelines
• Provided remote assistance with Network and System core configurations for the HPC Linux clusters, Linux servers and workstations at various customer locations.
• Built installers using Redhat Package Manager RPM , rpmbuild for CentOS/Redhat installations and custom installers for other Linux distributions and managed patch builds and maintenance for various packages.

• Built HPC production clusters, using ROCKS and Scyld cluster ware software and involved in tech/production support.
• Emulated HPC cluster using VMware for development team.
• Integrated 15TB SCSI storage using NFS and Samba over the network for each cluster.
• Managed user accounts using NIS and YP over LAN, WAN.
• Extensively used IPMI, SNMP protocols, raid 5, 10 configurations for storage and shell scripts to monitor system health which includes NAGIOS, dell open-manage software.
• Involved in testing and benchmarking clusters for different environments.
• Monitor and model system stability, and throughput performance.
• Maintained SAMBA, Apache, LDAP, DHCP, Mail postfix , Tomcat, MySql and file servers.
• Worked with IPMI, switched rack PDU's and remote access UPS for monitoring systems health.
• Duties also include custom scripting, documentation of processes and systems.
• Created custom rolls for ROCKS OS clusters.
• Ported ROCKS installation to scyld cluster ware.
• Implemented SAMBA and NFS over NAS and SCSI attached storages.
• Performed Kernel Tuning, Performance Analysis/Tuning and troubleshooting.
• Include administration, integration and maintenance of all HPC cluster configurations, storage systems, backup systems, and network peripheral devises.
• Analyzed numerous hardware/vendor servers for HPC and production environment.

• Implemented and Managed LAN/WAN heterogeneous networks.
• Perform hardware/software maintenance for colocated servers, including equipment replacement and capacity planning.

• Created test-environment and built new servers based on the application requirement as a major task that were implemented on a weekly basis.

• New UNIX/Linux server setups Kickstart/Jumpstart , Kernel tuning, Hardware upgrading and System installation software installing, patch management.
• Veritas Volume Manager and NFS are extensively used.
• Designed and maintained a high availability cluster of IBM Xseries and IBM bladecenters servers to provide high-volume, dynamic WWW content with greater than 99 availability.
• Maintained internal and customer secondary DNS Linux / Bind, NIS, TCP/IPv4 .
• Administration of various systems in the heterogeneous network, which includes day to day maintenance using Cron jobs, log checks, scripting Shell , performance monitoring.
• Created and maintained Cisco router access list / firewall.
• Communicating, escalating and resolving problems in the integration, staging production environments.