Note: The job is a remote job and is open to candidates in USA. Dice is presenting a contract opportunity supporting an IT Datacenter organization and its HPC and Electronic Design Automation infrastructure. The Senior DevOps Engineer will independently administer Linux HPC platforms, automate infrastructure with Ansible, manage SLURM environments, execute datacenter migrations, and integrate enterprise identity, storage, monitoring, and documentation systems.
Responsibilities
- Support and administer SLURM-based HPC compute environments, including partition configuration and migration planning
- Plan and execute HPC/EDA compute and storage infrastructure migrations across datacenters
- Develop migration strategies and evaluate implementation options, risks, dependencies, and operational tradeoffs
- Author formal Method of Procedure (MOP) documents and runbooks for infrastructure changes and service cutovers
- Coordinate cross-functionally with EDA/SPE teams, storage teams, and IDAM to deliver coordinated platform changes
- Verify storage volumes, application access, and service continuity following migrations or infrastructure changes
- Define HPC storage service tiers and gather performance and capacity requirements for EDA workloads
- Administer SUSE Linux Enterprise Server (SLES) 12 and SLES 15 systems in a production HPC environment
- Build and maintain custom Linux OS images and installation media using Kiwi NG and related tooling
- Enable and maintain bare-metal provisioning workflows via RackN / Digital Rebar Provision for SLES and ESXi deployments add PXE
- Provision and configure VMware vSphere virtual machines for HPC service workloads
- Troubleshoot production issues in Linux HPC operational scripts, services, and system daemons
- Develop, maintain, and extend Ansible playbooks and roles for Linux system setup, authentication, and platform configuration
- Ensure multi-version Ansible playbook compatibility across SLES 12 and SLES 15
- Manage Git repositories and Artifactory artifact storage; migrate large binaries and configuration artifacts out of source control
- Contribute GitHub pull requests, conduct code reviews, and manage inner-source infrastructure repositories
- Drive production environment changes through change management workflows using ServiceNow
- Integrate and configure enterprise identity systems including Okta, Active Directory, LDAP, NIS, VAS, and SSSD for Linux/HPC environments
- Audit and reconcile Linux user and group identity data (UID/GID) across multiple directory and authentication domains
- Validate authentication methods and access behavior across HPC compute and storage environments
- Extend SSSD-based corporate authentication to new compute environments and author corresponding Ansible automation
- Assess and implement log management strategies, including evaluation of Splunk integration for HPC system logs
- Investigate and remediate operational issues in production Linux services (VNC, NIS, AutoFS, Zabbix, etc.)
- Produce technical documentation, architecture diagrams, implementation guides, and end-user instructions in Confluence
Skills
- 5+ years of experience in a DevOps, Platform Engineering, or Linux Systems Engineering role
- Hands-on HPC cluster administration experience, including SLURM or equivalent workload managers
- Demonstrated experience supporting EDA or scientific computing environments
- Strong Ansible automation skills with production-grade playbook and role development
- Experience with bare-metal provisioning tools (RackN, Cobbler, or equivalent)
- Proven ability to plan and execute datacenter or infrastructure migrations with minimal disruption
- Familiarity with enterprise Linux identity and authentication stacks (SSSD, LDAP, AD, NIS, Okta)
- Experience with NetApp or comparable enterprise storage platforms in HPC contexts
- Ability to author formal technical documentation (MOPs, runbooks, architecture diagrams)
- Strong written and verbal communication skills; capable of coordinating across multiple teams
- Experience with SUSE Linux Enterprise Server (SLES) 12 and/or 15 in an enterprise environment
- Familiarity with RackN / Digital Rebar Provision for bare-metal OS deployment
- Hands-on experience with Kiwi NG or similar tools for custom OS image creation
- Knowledge of VMware vSphere for HPC support VM provisioning
- Experience migrating configuration artifacts and binaries to Artifactory
- Background in semiconductor, storage, or high-tech manufacturing IT environments
Benefits
- Remote (100%)
Company Overview