CTO-track Founding Infrastructure Engineer, GPU Scheduling

About the job Natilah is building AI optimization layers for GPU infrastructure. Help GPU clusters improve utilization, queue times, scheduling efficiency, and infrastructure performance, starting with safe read-only shadow testing. Looking for a CTO-track Founding Infrastructure Engineer with strong experience in Kubernetes, GPU scheduling, distributed systems, DevOps, or AI infrastructure. This is not a generic full-stack role. The ideal person has worked with Kubernetes internals, schedulers, controllers, operators, CRDs, RBAC, GPU clusters, NVIDIA GPU Operator, Slurm, Ray, Kueue, Volcano, Run:ai-like systems, or production AI infrastructure. The first mission will be to help prepare for safe shadow deployment with real GPU infrastructure partners. That means designing and validating the Kubernetes integration, read-only cluster observation, scheduling recommendation logs, safety checks, baseline comparisons, deployment structure, and technical roadmap. Responsibilities: Design the shadow deployment architecture. Define how to observe clusters' states without mutating production. Work on Kubernetes integration, RBAC, observability, and safety boundaries. Help validate scheduling recommendations against baseline schedulers. Improve technical readiness for pilots with GPU infrastructure partners. Review and strengthen architecture, reliability, testing, and deployment practices. Help define the technical roadmap toward production readiness. Eventually lead the engineering direction if there is a strong mutual fit. Strong fit if you have experience with: Kubernetes scheduling, controllers, operators, or CRDs. GPU infrastructure and multi-tenant GPU clusters. NVIDIA GPU Operator, MIG, CUDA workloads, or GPU allocation. Kueue, Volcano, Slurm, Ray, KubeRay, Run:ai, or similar systems. Distributed systems and resource allocation. AI infrastructure, MLOps, inference, training clusters, or model serving. Datacenter, bare-metal, cloud, or HPC infrastructure. Production reliability, observability, and infrastructure security. This is an early-stage, pre-incorporation founding role. The MVP exists, and the company is currently being structured. The role would start with a serious technical trial before any final title, equity, or long-term commitment is agreed. Compensation and equity: This is a founder-level opportunity. Cash compensation is not guaranteed at the start and will depend on funding, company formation, and the final role structure. Equity is possible for the right person, subject to role, commitment, contribution, vesting, and legal agreements. Any equity would vest over time and would not be immediate. Hiring process: Intro call. Technical fit discussion. Short pre-NDA architecture task around read-only shadow deployment. NDA and limited technical review if there is a strong fit. Final discussion on role, commitment, compensation, and equity structure. Applicant privacy: Any information shared during the process will only be used to evaluate fit for this role. It will not be shared externally without permission.