Help us build the next big ideas in today's cloud computing industry
Cloud Architect - HPC
About The Position
Spotinst is a dynamic, fast growing technological startup with headquarters located in Tel-Aviv and additional offices in San Francisco, New York, Washington D.C. and London. With innovative technology that is revolutionizing the cloud computing industry and a team of highly motivated and creative employees, our vision is to optimize the way DevOps and R&D teams consume cloud computing.
Spotinst is seeking a Cloud Architect - High-Performance Computing (HPC) to join our office in the US. A challenging role that includes working with multiple stakeholders and has a direct influence on Spotinst’s product.
- Researching and designing cloud-native integrations for systems such as Grid Engine, IBM Symphony, and/or PBS Pro
- Responsibility for the integration of HPC workloads on clouds such as AWS, Azure, and GCP with focus on dynamic infrastructure and Spotinst’s cost aware computing platform
- Transiting concepts from ideas to working prototypes with the full support of the appropriate engineering resources
- 5+ years of HPC experience - MUST
- 5+ years of experience with Linux/Unix variants, especially RedHat/RHEL and its derivatives
- 5+ years of experience supporting high-performance clusters with Grid Engine (any variant), Symphony or Slurm
- Scripting experience (Go, Python, R, bash, etc)
- Automation/configuration management experience (Puppet, Ansible, Chef, Salt, etc.)
- Able to clearly present ideas to both technical and non-technical users in formal and informal settings
- Demonstrated decision-making skills and leadership ability to assist with the management of project portfolio and daily operations for the team
- Multi-vendor servers running Red Hat, CentOS or Windows
- File systems knowledge such as Lustre, ZFS, GPFS, btrfs, XFS, hand ext3/4
- Designs, codes, tests, debugs, maintains, modifies and documents HPC solutions.
- Identifies and resolves complex systems problems relating to the scalability of HPC solutions.
- Installs, tests, evaluates and integrates HPC applications and third-party products.
- Conducts and coordinates the analysis, planning, and implementation of HPC systems software.
- Researches new technology for potential implementation, to be given to senior management.
- An understanding of the Cloud platforms and a passion for automation
- Capable of producing code that will support Proof of Concepts and Minimal Viable Products
- Produce quality documentation of use cases, business, and technical solutions and concepts
- Present to and solicit feedback from various engineering, development and operations teams
- Work with product teams in an advisory capacity to understand current products and roadmaps to help these teams develop innovative future offerings
- Work with existing engineering and operations teams to understand existing infrastructure and offers, and take advantage of current best practices
- Gather extensive feedback from customers as part of researching and developing proof-of-concept offerings
- SAN/NAS hardware experience
- Experience running parallel jobs with OpenMP or MPI
- Knowledge of GPU computation and CUDA Experience configuring and running Bright Cluster Management Software
- Experience supporting LDAP/IPA, NFS, Samba, Web servers