Cloud Infrastructure Engineer (AWS)

TL;DR

Cloud Infrastructure Engineer (AWS/Kubernetes): Designing and operating foundational cloud primitives and networking fabric to power AI products with an accent on security, isolation, and multi-region scalability. Focus on building secure deployment topologies for enterprise customers, scaling mixed CPU/GPU fleets, and automating day-2 operations.

Location: London, Belgrade, or Berlin

Company

hirify.global is an AI search engine company building high-performance infrastructure to support LLM-driven products for consumers and enterprises.

What you will do

• Own the technical strategy and roadmap for agent-driven cloud infrastructure management.
• Design and operate the cloud networking fabric, including VPC architectures and peering with hyperscalers for low-latency AI workloads.
• Architect and scale compute platforms using Kubernetes/EKS and mixed CPU/GPU fleets across multiple regions.
• Build and maintain secure, isolated deployment topologies for multi-tenant and customer-owned cloud (BYOC) environments.
• Implement multi-region strategies for availability, failover, and disaster recovery.
• Develop automation, tooling, and runbooks using Terraform and software engineering in Python, Go, or Rust.

Requirements

• 7+ years of industry experience building and operating production cloud infrastructure.
• Deep experience with AWS VPC design, routing, security groups, and load balancing.
• Strong background with Kubernetes/EKS in multi-cluster, multi-region, or multi-account setups.
• Experience building secure, isolated environments for enterprise customers (BYOC, BYOK/KMS integrations).
• Proficiency with Terraform and strong software engineering skills in Python, Go, or Rust.
• Strong debugging and incident management skills across distributed systems.