HPC and Research Computing Engineer
The Okinawa Institute of Science and Technology (OIST) is an Independent Administrative Institution established by the Government of Japan. Its aim is to establish a world‐class university of science and technology in Okinawa. English will be the language of instruction and a large segment of the faculty and student population will be international. Currently, 51 Faculty and a total of more than 360 Scientists, Technicians, Postdoctoral Scholars, Students, and Research Support staff are located in OIST facilities in Onna, Okinawa. We seek an experienced unix administrator for Scientific Research to provide technical leadership and oversight of computer systems in support of scientific research activity.
Location
Responsibilities
This role will see members interacting daily with world leading researchers, supporting and enhancing their usage of OIST's substantial HPC and Scientific Computing Services.
Under the direction of the Scientific Computing Section Leader the member will consult directly with researchers at OIST to support their use of OIST scientific computing resources. This will involve day to day management of OIST HPC clusters and researcher services, educating and advising researchers, as well as general systems administration and programming tasks.
- In particular, duties will involve:
- Installing, configuring, and maintaining large computer clusters
- Day to day administration and operation of OIST HPC clusters
- Management of clusters/servers network switch, storage filesystems and HPC software stacks
- Diagnosing and resolving hardware issues effectively
- Coordinating with vendors to resolve hardware and software problems
- Rebuilding and reconfiguring nodes/servers as appropriate
- Building and deploying open source and vendors’ software
- Managing cluster and storage systems usage
- Supporting users in accessing the cluster and resolving issues with jobs
- Tuning cluster and scheduler settings as directed by the SCS Leader
- Monitoring and maintaining usage and security of the clusters and servers
- Documenting system administration procedures for all tasks
- Other duties as assigned by the SCS Leader
- Other research systems administration tasks as appropriate, including;
- Managing virtual machine deployments
- Deploying web services
- Managing and maintaining test systems
- Mirroring and deploying research databases or collaborative tools
- Investigating new technologies and systems as directed
Qualifications
(Required)
- BS or MS degree in science or engineering, and at least 6 (BS) or 3 (MS) years of Unix/Linux experience, with experience in HPC system administration or in managing large HPC clusters.
- Experience in high-performance research computing and in-depth understanding of the following: Unix and Linux architecture, queuing systems and schedulers; networking infrastructure issues and storage solutions related to HPC; system tuning, and data backup and security issues.
- Solid teamwork skills
- Fluent in spoken and written either in English or Japanese.
(Preferred)
- Experience in installing, configuring and maintaining cluster job scheduler (such as SLURM, PBS, LSF, etc.).
- Experience working with one or more parallel file systems (such as, Lustre, GPFS, Spectrum scale, etc.)
- Experience in deploying hardware in data center, provisioning server system using configuration management tools (Puppet, Chef, etc.), setting system health monitoring (Nagios, Ganglia, Zabbix, etc), and out-of-band management (IPMI, iDrac, iLO, etc.)
- Experience working with Infiniband (concepts, OFED layers, switches, etc.)
- Experience in installing open sources software, MPI libraries and installing and supporting HPC compilers and libraries.
- Experience in designing system solution, contacting vendors, writing specification, following up maintenance support with vendors
- Experience in a research environment, particularly in providing support to researchers on their HPC computation
- Other desirable skills include familiarity with grid computing; knowledge of high-level scripting languages such as Python and Perl; knowledge of web server technology; proficiency in project planning and project management; ability to work independently as well as collaborate with end users and other system administrators.
Term
Starting Date
Working Hours
Compensation
In accordance with the OIST Employee Compensation Regulations
Annual salary: 4.2 million yen ~ 6.6 million yen (Job class: Administrative staff III, A3)
Benefits
- Relocation, housing and commuting allowances
- Annual paid leave and summer holidays
- Health insurance (Private School Mutual Aid http://www.shigakukyosai.jp/ ), welfare pension insurance (kousei-nenkin), worker’s accident compensation insurance (roudousha-saigai-hoshou-hoken)
Submission Documents
- Curriculum vita in English (and Japanese if available)
* Please be sure to indicate where you first saw the job advertisement.
Application Due
Postal Address
Recruiting Team, HR Management Section
Okinawa Institute of Science and Technology Graduate University
1919-1, Onna, Onna-son, Okinawa 904-0495, Japan
Email Address
Declaration
* OIST Graduate University is an equal opportunity, affirmative action educator and employer and is committed to increasing the diversity of its faculty, students and staff. The University strongly encourages women and minority candidates to apply.
* Information provided by applicants or references will be kept confidential, documents will not be returned. All applicants will be notified regarding the status of their applications.
* Please view our policy for rules on external professional activities (https://groups.oist.jp/acd/information-disclosure/).
* Further details about the University can be viewed on our website (www.oist.jp).