High Performance Computing (HPC) Engineer - Saudi Arabia

HIGH PERFORMANCE COMPUTING (HPC) ENGINEER - INFINIBAND EXPERIENCE ESSENTIAL

An excellent opportunity to work in Saudi Arabia, for 3-6 months. Candidates from Pharma/Higher Education/Banking sectors favorable.

JOB DESCRIPTION:

The HPC Systems Engineer will maintain both hardware and software on High Performance Computing Cluster (HPC Cluster/HPCC) in active production.

The position requires an individual who has worked in large-scale computing environments (500+ Servers) with an emphasis on distributed computing and high speed interconnects (Infiniband, 10gig Ethernet, etc). Linux HPC/distributed computing experience is required.

This individual must work on complex issues where analysis of situations or data requires an in-depth evaluation of variable factors.

RESPONSIBILITIES:

The HPC Engineer will perform such tasks as:

- Hardware maintenance, repairs, service-related issues, and hardware troubleshooting.
- Setting up and troubleshooting node network connections, including:
- DHCP & PXE,
- Gigabit and 10-gigabit Ethernet,
- Layer 2 and Layer 3 routing & switching (including VLANs),and Infiniband (QDR & DDR).
- Management of the VMWare ESX infrastructure.
- Advanced troubleshooting of issues clients and users experience through to completion and resolution, including vendor escalation when necessary.
- Management of the HPCC datacenter and infrastructure, including cable management, rack power and heat management, UPS implementation and management, an understanding of large-scale power distribution, and experience with water or refrigerant-based liquid cooling systems (Liebert systems are ideal)
- Management and utilization of cluster-wide hardware and software monitoring systems including HP SIM.
- Development and implementation of patch deployment and management tools and services, and hardware and software life cycle management.
- Design and planning for expansion and future growth.

KEY QUALIFICATIONS:

Required:

- An expert-level understanding of computing/server hardware. Applicant should have an in-depth understanding of system components (processor, memory, hard drives & RAID arrays, networking) and their inter-relation, and have extensive experience with troubleshooting and diagnosing failures of said components from the OS to hardware levels, and opening service calls with HP seeing through to resolution.

Required:

- An expert-level understanding of the OSI network model, TCP standard, IP Addressing (including supernetting and superscopes), 10-gig networking, layer 2 switching (including VLANs), and layer 3 routing.
- Experience in detailed network design and operations, including routing, switching, layer 2 and 3 equipment, WANs, Multicast, DNS, and Active Directory.
- Extensive experience with HP blade chassis hardware and networking.
- Extensive experience with OOBM controllers, such as DRAC and iLO, and remote IPMI management.
- A solid understanding of Active Directory, Group Policy management, WMI, and Linux Shell Scripting.
- Extensive experience with VMWare ESX or similar Hypervisor products in a production environment.
- Experience in designing and managing mid- to large- file storage systems (both block level storage and file level storage).
- Experience in managing large-scale multi-vendor projects and deployments.
- An in-depth understanding of Infiniband networking, troubleshooting, and management practices and protocols. (OpenSM experience is preferred.)
- Experience managing and handling sensitive and proprietary data, and implementing data security best practices.