AI Systems Architect (AI)

Location: Remote

Company

hirify.global is a global web hosting and cloud infrastructure company providing VPS, dedicated servers, shared hosting, domains, game servers, and cloud-based infrastructure.

What you will do

• Define and execute the AI roadmap and build reusable AI platforms, services, agents, copilots, APIs, and automation systems.
• Design and operate GPU-enabled infrastructure using Linux, Proxmox VE, KVM, virtual machines, containers, and Docker.
• Deploy, benchmark, optimize, and operate self-hosted and commercial LLMs, including model gateways and inference APIs.
• Build production RAG systems, vector-search solutions, agentic workflows, internal assistants, and customer-facing AI applications.
• Integrate AI with hosting infrastructure, customer portals, databases, billing, support, monitoring, and internal business systems.
• Establish secure, observable, resilient production systems with approval gates, access controls, audit trails, and rollback mechanisms.

Requirements

• At least 5 years of hands-on experience in infrastructure, platform engineering, DevOps, SRE, cloud, backend systems, virtualization, or production systems administration.
• At least 2–3 years of practical experience building, deploying, operating, or integrating AI-powered applications, LLM systems, or AI infrastructure.
• Strong Linux, Docker, virtualization, networking, production troubleshooting, monitoring, backup, and disaster-recovery knowledge.
• Practical experience with GPU workloads, LLM deployment, inference optimization, RAG, embeddings, vector search, agents, tool calling, and structured output validation.
• Strong scripting or programming experience with Python and/or JavaScript/TypeScript/Node.js, plus experience integrating APIs, databases, webhooks, and backend services.
• Professional working proficiency in English and the ability to work independently in a fully remote environment are required.

Nice to have

• Proxmox clustering, Proxmox Backup Server, KVM, PCIe/GPU passthrough, ZFS, Ceph, or distributed storage experience.
• NVIDIA CUDA, vLLM, Ollama, LiteLLM, TGI, Triton, quantization, LoRA, multi-GPU inference, or model-routing experience.
• Experience with LangChain, LangGraph, LlamaIndex, Qdrant, pgvector, Weaviate, Milvus, Pinecone, Terraform, Ansible, Kubernetes, or CI/CD platforms.
• Experience with hosting platforms, customer portals, billing systems, WHMCS, cPanel/WHM, observability, secrets management, or infrastructure security.

Culture & Benefits

• Fully remote individual-contributor role with significant technical ownership and architectural influence.
• Close collaboration with the CTO and Product, Engineering, Infrastructure, Operations, Support, and business teams.
• Focus on measurable technical and business value rather than experimentation for its own sake.
• Opportunity to shape AI adoption across infrastructure, products, customer experience, sales, support, and internal operations.