Founding Engineer

Founding / Early Engineer – Real-Time AI Systems (Healthcare) We’re building something that doesn’t exist today: real-time AI that runs inside a doctor’s office . Today, AI in healthcare mostly lives in the cloud. It helps with notes and paperwork—but it’s not present when decisions are made. That’s because clinics don’t have the power, cooling, or infrastructure needed to run high-performance systems. We’re changing that. We’re building GPU-powered systems that run locally , inside clinical environments, enabling AI to operate in real time during patient care. This is a move from prototype to production, and early engineers will define how the system works end-to-end. What You’ll Do You’ll take ownership of systems from start to finish, working across: Infrastructure (running GPU compute in constrained environments) Backend systems & integrations (making messy clinical software actually work) This is not a narrow role—you’ll work across hardware, infrastructure, and application layers to build systems that are reliable in the real world. Must-Have Technical Expertise We care about deep understanding and systems thinking , not just tool familiarity. You should be able to explain how these technologies work together in real, production systems. This role is CUDA-centric . Our entire system runs on NVIDIA GPUs. Required experience: TensorRT PyTorch C++ Low-level performance optimization (memory, compute, thermals, etc.) Kafka Python TensorFlow Rust and/or Golang What You’ll Be Building Private, local AI systems (runs inside the clinic, not the cloud) Edge deployments (works in constrained environments with limited power/cooling) Decentralized AI infrastructure (data stays local and owned) Systems that remain stable under real-world conditions What Makes This Role Different You own outcomes , not tickets You’ll work with incomplete specs and real constraints (power, heat, noise) There is no clean separation between hardware, infra, and software If the system fails, care is impacted —reliability matters What We’re Looking For Candidates coming from NVIDIA OR FAANG Experience building and owning production systems under real load Strong systems thinking (understanding failure modes, performance, tradeoffs) Ability to operate in ambiguity without a playbook 401(k) #J-18808-Ljbffr Stealth AI Infrastructure Startup