Senior AI Infrastructure Engineer

The role

You will own the platform including the model gateway, runtime for production agents, clusters, data stores, pipelines, secrets, and release paths. You will manage AI infrastructure, core platform stability, reliability, and security.

What you will do

• Run the model gateway including routing, fallbacks, and rate limits
• Make the gateway multi-tenant with usage metering and reconciliation
• Run the AI developer platform and remote workspaces
• Run production agents safely using sandboxing and credential scoping on Kubernetes
• Automate infrastructure workflows and infra agents
• Own infrastructure and AI spend
• Keep clusters and cloud healthy using EKS, AKS, k3s, and Terraform
• Run the edge using Cloudflare
• Ship new services fast through GitOps
• Lead migrations between regions, clouds, and platforms

Required qualifications

• 5+ years running production infrastructure, with real on-call experience
• Deep Kubernetes debugging, including stateful workloads, and hands-on experience running Kubernetes on bare metal
• Hands-on work with LLM APIs in production
• Experience handing real operational work to agents or automation
• Enough Go or Python to read an unfamiliar codebase and ship a fix
• Hands-on observability with Grafana, Prometheus and OpenTelemetry collectors
• GitOps and Terraform in production
• Networking fundamentals: DNS, TLS, load balancing, WAF and routing
• Experience taking a third-party service to production end to end
• Experience leading a region, cloud or database migration with a tested rollback
• Experience cutting a real cloud or AI bill
• Security judgment: least privilege, secret handling, credential rotation, safe rollouts

Nice to have

• LiteLLM or a similar LLM gateway
• LLM serving, such as SGLang or vLLM
• Multi-tenant API platforms, including metering and billing
• Data pipelines, such as Airbyte, Airflow or CDC into BigQuery
• Realtime audio or WebSocket services
• Agent sandboxing, such as gVisor, Landlock or agent-sandbox
• Langfuse or other LLM tracing
• Remote dev environments, such as Coder
• FinOps across several clouds
• Mandarin

About the company

Hellyeah is the agentic operating system for distribution. AI agents plan, execute and optimize growth work, and humans approve it.