About the job
Artificial intelligence is moving from passive assistance to autonomous, always-on agentic workflows. Our mission is to make this transition flawless, high-performing, and secure for millions of users worldwide, running natively on the GPUs already sitting in their PCs. We are looking for a Senior Software Engineer to build and optimize the local runtimes and agent frameworks that bring autonomous AI to Windows and NVIDIA GeForce RTX GPUs.
Responsibilities
Optimize performance of local LLMs (Nemotron and others) on GeForce RTX hardware. Profile and optimize inference across Ollama, llama.cpp, and vLLM, minimizing latency and memory footprint using TensorRT and CUDA.
Build and optimize agentic harnesses (NemoClaw, OpenClaw) to run natively and reliably on Windows. Implement the orchestration logic that lets multi-agent systems plan, act, and use tools efficiently on constrained consumer hardware.
Implement policy-based privacy and security frameworks for autonomous agents, handling filesystem access, secure inference routing, and network egress within thorough sandboxed execution environments.
Work close to the metal, integrating agent and inference stacks with NVIDIA's driver and middleware layers to extract maximum performance from RTX GPUs.
Partner with internal AI research teams, driver teams, and the open-source OpenClaw community to ensure our consumer hardware is the best possible platform for local agents.
Write reliable, production-ready code, contribute to engineering best practices, and raise the technical bar through code review and design input.
Qualifications
Minimum
12+ years of relevant professional software engineering experience, with a track record of shipping performance-critical systems.
BS, MS, or PhD in Computer Science, Computer Engineering, or a related technical field (or equivalent experience).
Hands-on experience with LLM inference pipelines (Ollama, llama.cpp, vLLM), GPU-accelerated computing (CUDA, TensorRT), and running local models on consumer-grade hardware.
Practical experience with modern agentic frameworks (e.g., OpenClaw, LangChain, AutoGPT) and a working understanding of how multi-agent systems plan, act, and use tools.
Strong understanding of Windows OS internals, process isolation, sandboxing technologies, and system-level security.
Proficiency in C++ (performance-critical systems and OS integration), Python (AI and orchestration logic), and TypeScript (agent plugins and tooling).
Ability to translate complex technical decisions into clear documentation and collaborate effectively across diverse engineering teams.
Preferred
Demonstrated open-source contributions to AI agent platforms or inference/orchestration tools (especially OpenClaw or llama.cpp).
Deep knowledge of NVIDIA GeForce RTX architecture and its specific constraints and advantages for edge AI.
Experience building virtualization, containerization, or sandboxing tools natively for Windows.
Active technical community presence (blogs, talks, whitepapers) at the intersection of AI, security, and local compute.