Jobistas is currently seeking on behalf of our client, a new Athens-based software company specializing in enterprise AI infrastructure, a Lead DevOps / Site Reliability Engineer. The company is redefining how organizations interact with AI by empowering them to build high-level workflows while maintaining absolute data control through SaaS or secure On-Premise deployments

The Mission

Your primary goal is to build a “write once, deploy anywhere” infrastructure. You will bridge the gap between our high-performance AI models and the diverse environments of our enterprise clients.

Key Responsibilities

• Hybrid Deployment Architecture: Architect and maintain Kubernetes-based deployment patterns that work seamlessly across AWS/GCP (SaaS) and private data centers (On-Prem).
• Privacy-First Infrastructure: Implement strict data isolation, encryption at rest/transit, and VPC-peering strategies to meet enterprise-grade compliance (SOC2, HIPAA, or GDPR).
• Packaging for On-Prem: Master the art of Helm charts, Kustomize, and container bundling to ensure “one-click” installs for customers with limited internet access (air-gapped environments).
• AI Resource Optimization: Manage GPU-accelerated workloads (NVIDIA/CUDA) within Kubernetes to ensure our AI workflows are performant and cost-efficient.
• Observability: Build a unified monitoring stack that provides Omen with insights into SaaS health while respecting the “no-phone-home” constraints of On-Prem clients.

Technical Stack Requirements

Why You’re a Great Fit

• The “Architect” Mindset: You understand that On-Prem isn’t just “SaaS on a different computer”—you anticipate the networking, storage, and permission hurdles of a locked-down enterprise environment.
• Security Paranoid: You believe that data privacy isn’t a feature; it’s the product. You default to “least privilege” in every configuration.
• Startup Agility: You are comfortable moving fast, wearing multiple hats, and building the “v1” of our deployment automation from scratch.