Senior AI Infrastructure Engineer

CloudCraft Labs Products Overview UniCraft GovCraft AgentCraft AI ToolMesh Services Features Customers Pricing About Overview Stories Blog Careers Book a demo Products Overview UniCraft GovCraft AgentCraft AI ToolMesh Services Features Customers Pricing About Overview Stories Blog Careers Book a demo → ← All roles Engineering Senior AI Infrastructure Engineer Remote Full-time Own the core of UniCraft and the platform it runs on — the routing layer, the cache, and the self-hosted footprint that makes it all run inside customers' own clouds. Apply by email →All roles What you’ll do Design and own the UniCraft routing layer that selects the best model per request across 12+ providersBuild the semantic cache, automatic failover, and provider-arbitrage logic that keep cost and latency downMake the stack run cleanly inside customer clouds — Kubernetes, GPU scheduling, autoscaling, and safe upgradesInstrument everything around cost-per-resolved-task, not just raw latency What we’re looking for 5+ years building high-throughput backend or infrastructure systems in productionStrong Python and distributed-systems fundamentals; comfortable with async and streamingHands-on Kubernetes and cloud (AWS / GCP / Azure) experienceA bias for measuring before optimizing Nice to have Experience with LLM inference, GPU scheduling, or model servingPrior work on multi-tenant, self-hosted software How to apply Email your resume to info@cloudcraftlabs.com with the role title in the subject line. A real engineer reads every application and replies within a few business days. Apply by email → What you’ll do Design and own the UniCraft routing layer that selects the best model per request across 12+ providersBuild the semantic cache, automatic failover, and provider-arbitrage logic that keep cost and latency downMake the stack run cleanly inside customer clouds — Kubernetes, GPU scheduling, autoscaling, and safe upgradesInstrument everything around cost-per-resolved-task, not just raw latency What we’re looking for 5+ years building high-throughput backend or infrastructure systems in productionStrong Python and distributed-systems fundamentals; comfortable with async and streamingHands-on Kubernetes and cloud (AWS / GCP / Azure) experienceA bias for measuring before optimizing Nice to have Experience with LLM inference, GPU scheduling, or model servingPrior work on multi-tenant, self-hosted software How to apply Email your resume to info@cloudcraftlabs.com with the role title in the subject line. A real engineer reads every application and replies within a few business days. Apply by email → CloudCraft Labs An AI products company. We build enterprise-grade AI that teams own outright — routing, governance, voice, and trusted tools — deployable on your own cloud. Products UniCraftGovCraftAgentCraft AIToolMesh Company AboutCustomersPricingCareersBlog Get in touch info@cloudcraftlabs.com512-991-3999Book a demo → © 2026 CloudCraft Labs LLC. All rights reserved.30.2672° N, 97.7431° W — Austin, Texas Route AI Govern AI Voice AI Trust your tools