Senior Engineer - AI Agents and Systems

NVIDIA · Semiconductors · Santa Clara, CA +1

Senior Engineer role focused on deploying advanced AI agent frameworks and local runtimes to Windows and NVIDIA GeForce RTX GPUs, ensuring open-source AI agents run locally, safely, and efficiently on consumer PCs, and creating the foundation of the desktop AI operating system.

What you'd actually do

  1. Act as the lead engineer for developing the agent frameworks natively on Windows environments. You will shape the technical roadmap to bring always-on, self-evolving AI assistants to GeForce RTX PCs and laptops.
  2. Lead the engineering efforts to optimize the agent runtimes for Windows. You will ensure that autonomous agents operate within thorough, policy-based privacy and security frameworks (e.g., handling filesystem access, secure inference routing, and network egress).
  3. Partner closely with internal AI research teams, driver teams, and the open-source OpenClaw community. Ensure our consumer hardware provides an excellent ecosystem for autonomous agents.
  4. Foster a collaborative engineering culture by mentoring other engineers, establishing best practices for AI agent deployment, and writing reliable, production-ready code.

Skills

Required

  • Windows OS internals
  • process isolation
  • sandboxing technologies
  • system-level security architecture
  • LLM inference pipelines
  • GPU-accelerated computing
  • local models on consumer-grade hardware
  • AI orchestration
  • agentic frameworks
  • multi-agent systems
  • C++
  • Python
  • virtualization
  • containerization
  • sandboxing tools

Nice to have

  • NVIDIA GeForce RTX GPUs
  • open-source AI agents
  • Nemoclaw
  • OpenClaw
  • Nemotron models
  • privacy routers
  • sandboxed execution
  • desktop AI operating system
  • Ollama
  • Llamacpp
  • vLLM
  • CUDA
  • TensorRT
  • Hermes
  • LangChain
  • tool use

What the JD emphasized

  • 10+ years of relevant professional software engineering experience, with at least 3+ years in Staff, or Lead Architect role.
  • Deep understanding of Windows OS internals, process isolation, sandboxing technologies, and system-level security architecture.
  • Proven understanding of LLM inference pipelines (Ollama, Llamacpp, vLLM), GPU-accelerated computing (CUDA, TensorRT), and experience running local models on consumer-grade hardware.
  • Practical experience with modern AI orchestration and agentic frameworks (e.g., OpenClaw, Hermes, LangChain) and an understanding of how multi-agent systems plan, act, and use tools.
  • Proficiency in multiple languages, particularly C++ (for performance-critical systems/OS integration) and Python (for AI/blueprint logic).
  • Experience building virtualization, containerization, or robust sandboxing tools natively for the Windows ecosystem.

Other signals

  • Deploying advanced AI agent frameworks and local runtimes to Windows and NVIDIA GeForce RTX GPUs
  • Lead the development to ensure open-source AI agents (like Nemoclaw and OpenClaw) run locally, safely, and efficiently on consumer PCs
  • Create the foundation of the desktop AI operating system