Senior Engineer - AI Agents and Systems

Build and optimize local runtimes and agent frameworks that bring autonomous AI to Windows and NVIDIA GeForce RTX GPUs. As a hands-on individual contributor, you’ll profile and improve LLM inference across Ollama, llama.cpp, and vLLM, implement sandboxed, privacy-aware agent execution, and integrate inference stacks with NVIDIA driver and middleware layers. Collaborate with AI research, driver teams, and the open-source OpenClaw community to deliver high-performance, secure desktop AI.