Machine Language and/or Infrastructure engineer for AI. PhD preferred. My architecture is not an AI product; it’s a runtime for governed, persistent AI systems (think: a control plane for model execution). I’m specifically looking for someone with deep experience in distributed systems or AI infrastructure. They should be able to tell me what large-scale systems or runtimes they’ve personally built or operated, their experience with AI inference infrastructure (vLLM, Triton, Ray, CUDA, etc.) or distributed compute and whether they’re more excited by building core infrastructure layers than by shipping user-facing AI applications. I'm building a cognitive runtime that enforces architectural invariants across LLM interactions (think "OS kernel for AI"). The technical challenge: runtime-level state management, cross-model cognitive continuity, deterministic governance, and eventually silicon implementation of core primitives. Looking for an engineering co-founder who can: - Design and scale distributed runtime architecture (Ray, Triton, inference infra) - Speak authoritatively on system architecture and formal verification - Eventually contribute to hardware acceleration (FPGA/ASIC design) Quick self-vetting questions: 1. Have you designed (not just used) distributed systems or runtimes? 2. Experience with inference optimization or GPU programming? 3. Familiar with hardware-software co-design or silicon implementation? 4. Comfortable writing technical specs and validation frameworks? If 3+ are "yes" and you're interested in co-founding (equity-based, full-time), let's talk. If not, no worries - high bar by design. We have 21 production-grade tests validating 6 architectural invariants. Happy to share details if there's mutual fit.