Site Reliability Engineer (AI)

TL;DR

Site Reliability Engineer (AI): Operating and scaling AI-first platform infrastructure on Kubernetes with an accent on production-readiness, observability, and automation. Focus on building CI/CD pipelines, managing AWS environments, and ensuring system reliability for enterprise-grade agentic systems.

Location: Must be based in Belgrade, Serbia (Hybrid)

Company

hirify.global provides intelligent network operations platforms that help global enterprises manage, secure, and optimize their critical network infrastructure.

What you will do

• Operate and scale Kubernetes (EKS) clusters for AI and cloud-native workloads.
• Design and maintain CI/CD pipelines using GitLab CI/CD for platform services.
• Implement observability systems including metrics, logs, and traces.
• Define and enforce SRE practices such as SLIs, SLOs, and incident response.
• Build and manage infrastructure using Terraform for repeatable deployments.
• Partner with development teams to ensure services are production-ready and scalable.

Requirements

• 5+ years of experience in SRE, DevOps, or Platform Engineering.
• Strong hands-on experience with AWS and Kubernetes (EKS).
• Proficiency in Python for automation and scripting.
• Solid understanding of AWS IAM, roles, policies, and cross-account access.
• Experience with Infrastructure as Code (Terraform) and CI/CD pipelines.
• Experience with on-call rotations and production incident management.

Nice to have

• Experience with AI/LLM or agent-based systems.
• Knowledge of RAG, vector databases, or knowledge systems.
• Experience running stateful workloads on Kubernetes (PostgreSQL, Redis).
• Multi-region AWS architecture experience.
• Cost optimization and capacity planning skills.

Culture & Benefits

• Professional development budget for career growth.
• Dedicated wellness days and wellness week.
• Lifestyle spending account and employee recognition program.
• Collaborative, supportive, and inclusive workplace culture.
• Commitment to work-life balance and employee well-being.