Infrastructure Engineer (AI)

Location: Prague, Czech Republic; on-site, with 4 days in the office and 1 day working from home

Salary: CZK 150K–300K per month, plus equity

Company

hirify.global is a fast-growing Series A startup building an open-source Agent Cloud infrastructure platform for AI labs and consumer and enterprise AI agents.

What you will do

• Build distributed systems for millions and billions of AI agents and concurrent sandboxes.
• Design an orchestrator that places sandboxes on the right nodes and supports live migrations.
• Keep sandbox startup latency below 200 milliseconds and scale the platform to millions and later billions of active sandboxes.
• Improve the developer experience of self-hosting the open-source platform.
• Build an observability stack with metrics starting at the virtual machine kernel level.

Requirements

• 5+ years of experience building distributed systems and operating infrastructure at serious scale, including 100K+ RPS, multi-region systems, or petabyte-scale data.
• Deep Linux internals expertise, including eBPF, CPU scheduling, memory management, and cgroups v1/v2.
• Experience with VM hypervisors such as Firecracker, QEMU, or KVM, including virtio, hypercalls, and nested virtualization.
• Strong systems programming skills in at least one of Go, Rust, or C/C++, including performance-critical code and low-level data and I/O structures.
• Production orchestration experience with Kubernetes, Nomad, or custom systems, including resource scheduling, bin packing, and noisy-neighbor problems.
• Expertise in performance optimization and networking, including CPU caches, p99 latency, L4/L7 load balancing, network namespaces, iptables/nftables, and secure multi-tenant network isolation.

Nice to have

• Experience with userfaultfd, copy-on-write, or lazy loading.
• GPU passthrough, PCIe device virtualization, or infrastructure for AI/ML workloads.
• Contributions to Firecracker, Cloud Hypervisor, or similar open-source projects.
• Experience with observability at scale, distributed tracing, or kernel-level metrics.

Culture & Benefits

• Work with an open-source codebase and help improve self-hosting documentation and community adoption.
• Collaborate with engineers who worked on Firecracker, Cognition, JetBrains, Zapier, and Wish.
• Healthcare, vision, and dental insurance.
• Unlimited paid time off and a 401(k).
• Additional perks for in-office employees.