High Performance Computing (HPC) System Engineer

Starting salary will be based on experience and credentials

Ann Arbor, MI

Description

The High Performance Computing System Engineer will assist a team of scientific researchers to design, build and maintain high performance computing (HPC) cluster, storage and networking HPC hardware at Dyson-Sakti3’s Ann Arbor office. In this role you will participate in developing, testing, and deploying high efficiency computing algorithms, data processing, and reproducible data workflows.

Market Overview

Dyson is a global technology company. Using a desire to make things work better as a catalyst for invention, our team of 3,000 engineers and scientists are passionate about developing technology that solves the problems others often ignore. From the world’s first bagless vacuum cleaner, to hand dryers that use 420mph sheets of air to remove moisture from hands, to a completely re-thought hair dryer with its motor in the handle, we are relentless about engineering better solutions. Dyson spends $8.8million a week on research and development and works with more than 40 universities worldwide to develop early-stage technologies.


Dyson has acquired 100% of solid-state battery pioneer Sakti3. Together they will supercharge research and development into the new battery platform, to engineer breakthroughs in performance for future Dyson technologies.

Function Overview

Recently recognized for 3 prominent awards in 2017, Sakti3 offers a rewarding environment for employees:
* AWE - Seal of Approval Award (Alliance for Workplace Excellence) "Winners show an outstanding commitment to overall workplace quality."
* 101 Best and Brightest Companies to Work For (by the National Association for Business Resources)
* 100 Cool Places to Work in Michigan (by Crains Detroit Business)

Accountabilities

Facilitate design, build and maintain high performance computing cluster:

  • Provide technical knowledge to design high performance computing cluster
  • Assist in identifying and organizing requirements and producing HPC cluster specifications
  • Source hardware solutions for designed HPC cluster specification
  • Create and document High Performance Computing Service Delivery processes
  • Setup and build high performance computing cluster
  • Manage HPC related software and hardware issues
  • Ensure that all HPC faults and changes are logged in the logging system
  • Establish and document troubleshooting process, and problem resolve process
  • Provide status updates to all users and manager when required
  • Coordinate and facilitate computing job submissions based on priorities and efficiency

Participate in developing, testing, and deploying high efficiency computing algorithm, data process, and data workflows:

  • Porting and optimizing in-house developed software on high performance computing cluster to satisfy project needs
  • Develop and run in-house developed software testing to ensure and maintain code quality
  • Participate in software lifecycle development using agile software development principle
  • Implement software in C/C++, Java, Perl, Python, Matlab, Fortran or similar computing languages
  • Interface with, configure, and optimize parallel file and object storage system
  • Integrate and test software and systems
  • Contribute to technical reports delivered to management teams
  • Continue developing and advancing high performance computing knowledge
  • Continue monitoring current development of high performance computing technologies
  • Mentor, train, and coach team members about high performance computing technologies

Skills

  • 4 years’ minimum professional experience in a high-performance computing related or similar job required
  • Demonstrated experience with configuring, deploying, and troubleshooting high performance computing cluster
  • Bachelor's degree required, Master's degree preferred
  • Experience in HPC architecture, engineering and implementation services for distributed compute and data solution is required
  • Experience in deploying, maintaining, optimizing and administering HPC environment is required
  • Experience with using Matlab distributed computing server is a plus
  • Experience with developing efficient parallel computing software is a plus
  • Understanding of parallel computing concepts, such as deterministic, probabilistic and adaptive load balancing, synchronization, shared vs. distributed memory computing architecture, MIMD/SIMD, and cache structure is a plus
  • Knowledge of MPI and Open MP is a plus
  • Knowledge of network and server administration and troubleshooting is a plus
  • Strong sense of urgency and customer focus
  • Ability to answer and evaluate hardware, software, networking, and other IT related issues
  • Excellent follow-up skills to see tasks through
  • Ability to lift up to 20 lbs.

Benefits Overview

Sakti, a Workplace Excellence Awardee (2016), has been recognized with IHS CERAWeek’s Energy Innovation Pioneer Award (2014), by MIT’s Technology Review Magazine as one of the Top 50 Most Innovative Companies (2012) and World’s Top Ten, representing the “energy” category (2011). The senior team has over 100 years’ collective experience in research, manufacturing, and leadership. The company is a spinout of the University of Michigan, where its founding team created laboratories, published over 100 papers on batteries and related mathematics and physics, and demonstrated its first early prototypes. Financed by Khosla Ventures, Dyson, General Motors Ventures, Beringea and Itochu Technology Ventures, the company has been recognized for its innovative approaches in the Wall Street Journal, Fortune, Scientific American, Inc., Time, Automotive Engineering, the New York Times, Washington Post, NPR and other media.

Posted: 11-Aug-2017

Facebook LinkedIn Twitter Google Plus Viadeo