5 days ago
Base Salary
$146k - $234k/yr
Responsibilities
- Deploy, configure, operate, and optimize large language models and enterprise AI model-serving environments.
- Build and operate bare-metal OpenShift or equivalent Kubernetes clusters and core platform services.
- Transition platform provisioning from manual installs to infrastructure-as-code using Terraform and Ansible.
- Monitor and troubleshoot model-serving and platform health, performance, capacity, logging, and alerting.
- Assess OpenShift versus Spectro Cloud and document licensing, operability, architecture, and sustainability tradeoffs.
- Implement STIGs and cybersecurity compliance requirements on platform infrastructure.
- Support OCONUS platform bootstrap activities, including physical hardware installation and configuration.
- Document platform architecture, configuration decisions, and operational procedures.
Requirements
- At least 12 years of experience with a BS/BA, 10 years with an MS/MA, or 7 years with a Ph.D.
- Experience in platform, systems, or integration engineering and hands-on Kubernetes-based container platforms.
- Practical experience deploying and operating AI models, including foundational inference and performance-tuning knowledge.
- Hands-on experience deploying and administering OpenShift or another enterprise Kubernetes distribution on bare metal.
- Proficiency with Terraform and Ansible for infrastructure provisioning and configuration management.
- Working knowledge of Spectro Cloud, VMware, or equivalent virtualization and cloud orchestration platforms.
- Understanding of container networking, storage, cluster security, and lifecycle management.
- Strong Linux administration skills, particularly with RHEL.
- US citizenship, an active DoD Secret clearance, and a DoD 8570/8140-compliant certification.
- Regular or recurring physical access to a DISA SIPR-accredited facility.
- Working understanding of agentic platform modeling, hosting, and services.
- Preferred qualifications include CKA or CKAD certification, HashiCorp Certified: Terraform Associate certification, GitOps experience with ArgoCD or Flux, and disconnected or OCONUS platform bootstrapping experience.
Benefits
- Occasional telework is available, but candidates must live within 50 miles of a listed work location.
- The role supports work involving national security missions and secure government environments.
Tech Stack
Categories
About Peraton
Peraton builds and integrates mission systems, cyber, space, and intelligence solutions for U.S. defense, intelligence, and civil agencies. It delivers enterprise IT, satellite and terrestrial communications, and spectrum management under government contracts. Founded in 2017, the company is headquartered in Reston, Virginia and is privately held by Veritas Capital.