Infrastructure Engineer, Kubernetes Specialist

About the role

TypeSafe AI is building reliable, large‑scale AI systems that power real‑world automation. As an Infrastructure Engineer you will own the global infrastructure that runs millions of AI inference requests, ensuring low‑latency, high‑availability service across multiple clouds.

Key responsibilities

• Design, deploy, and operate Kubernetes clusters across multiple regions and cloud providers.
• Build and maintain the platform that powers large‑scale LLM inference workloads.
• Own networking components including VPCs, peering, load balancing, DNS, service mesh, and CNI plugins.
• Manage GPU infrastructure and autoscaling for machine‑learning workloads.
• Write and maintain infrastructure‑as‑code using Pulumi (Python) and related tools.
• Operate and improve observability stacks: monitoring, alerting, tracing, and logging.

Required profile

• Deep production experience with Kubernetes at scale (networking, storage, scheduling, upgrades).
• Strong background in AWS cloud services.
• Hands‑on experience with infrastructure‑as‑code tools such as Pulumi or Terraform.
• Solid understanding of Linux networking concepts.
• Track record delivering high‑traffic production ML systems.
• Programming fluency, preferably in Python.

Required skills

• Kubernetes
• AWS
• Pulumi (Python)
• Terraform or similar IaC tool
• Python
• Linux networking (VPC, DNS, load balancing)
• Service mesh (Istio, Envoy)
• CNI plugins (Cilium)
• GPU provisioning and autoscaling
• Observability tools (monitoring, alerting, tracing, logging)