About the role

Role Overview

Infrastructure Engineer (Kubernetes) to build and operate the infrastructure behind large-scale LLM inference. You’ll own the systems that enable reliable, low-latency AI workloads used by millions of users.

Responsibilities

Design, deploy, and operate Kubernetes clusters across multiple regions and cloud providers
Build and scale infrastructure for global AI inference workloads
Own platform components including:
- Networking and load balancing
- Service mesh
- Observability (monitoring, logging, tracing)
- Cloud infrastructure for production systems
Manage GPU infrastructure and autoscaling for ML workloads
Build infrastructure using Infrastructure as Code tools (e.g., Python, Pulumi, Terraform)
Improve platform reliability and operational excellence

Requirements

Strong production Kubernetes experience
Deep AWS and cloud infrastructure knowledge
Experience with Infrastructure as Code (Pulumi, Terraform, etc.)
Solid Linux networking fundamentals
Python programming experience
Experience supporting high-scale production systems

Nice to Have

Experience with ML/LLM infrastructure, GPU scheduling, and/or Kubernetes networking (Cilium, Istio, Envoy)
Experience with multi-cloud environments

About Alexander Chapman

Alexander Chapman is partnering with a frontier AI startup building large-scale AI systems focused on reliability, reasoning, and autonomous decision-making. The company is backed by nearly $40M in Seed funding and is developing infrastructure that powers AI products at global scale.

Infrastructure Engineer - Kubernetes

Tags