Founding Cloud Infrastructure Engineer at Series A AI Context Infrastructure Startup

As the Founding Cloud Infrastructure Engineer, you will build the foundational layer for AI agents to reason over complex enterprise data. You will design and own multi-cloud architecture, production Kubernetes, and GPU-intensive ML pipelines from scratch, moving beyond maintenance to shape the core infrastructure of the next decade of agentic AI.

• Design and operate multi-cloud infrastructure using AWS, GCP, and Azure with a focus on VPC networking, IAM, and automated capacity planning.
• Architect and manage production Kubernetes clusters including node pool management, service mesh, and GitOps workflows using Terraform, Argo, and Istio.
• Build and scale distributed ML infrastructure for model serving using Ray and Ray Serve, optimizing GPU scheduling and performance for inference.

• 3-10+ years of infrastructure experience with deep expertise in production-grade Kubernetes, Docker, Helm, and Infrastructure-as-Code using Terraform.
• Hands-on experience building distributed ML systems or GPU-intensive workloads using frameworks like Ray and Ray Serve in a production environment.
• Strong software engineering background in Python or Go with the ability to build automated CI/CD pipelines and full-stack observability using Prometheus and Grafana.

• Founding opportunity to build a high-scale infrastructure layer from the ground up alongside senior engineers from LinkedIn, Meta, Visa, and Branch.
• Solve the critical "context gap" in enterprise AI by engineering systems that support real-time inference and domain intelligence for autonomous agents.
• High-velocity startup environment with Series A funding and active deployments across major enterprise sectors like insurance, travel, and technology.