Lead AI Agent OS Architect (Windows, Equity)

NVIDIA AI; Redmond (WA); On-site; USD 272,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA AI is seeking a Senior Engineer to lead the deployment of advanced AI agent frameworks and local runtimes on Windows and NVIDIA GeForce RTX GPUs. You will guide development so open-source AI agents operate locally, safely, and efficiently on consumer PCs, combining Nemotron models with privacy-focused runtimes.

The role requires deep expertise in Windows internals, LLM pipelines, and GPU acceleration.

Qualifications

• 15+ years of professional software engineering experience.
• At least 3+ years in staff or lead architect roles.
• Deep understanding of Windows OS internals and security architecture.
• Experience with LLM inference pipelines and GPU acceleration (CUDA/TensorRT).
• Experience with AI agent frameworks (OpenClaw, Hermes, LangChain).

Responsibilities

• Lead development of agent frameworks on Windows and GeForce RTX GPUs.
• Optimize agent runtimes within privacy and security policies.
• Collaborate with internal AI research, driver teams, and OpenClaw community.
• Mentor engineers and establish deployment guidelines; write production-grade code.

Skills

C++

Python

Windows OS internals

LLM inference

Multi-agent systems

Education

BS/MS/PhD in Computer Science or Computer Engineering

Tools

Ollama

Llama.cpp

vLLM

CUDA

TensorRT

OpenClaw

LangChain

Job description

NVIDIA AI is seeking a Senior Engineer to lead the deployment of advanced AI agent frameworks and local runtimes on Windows and NVIDIA GeForce RTX GPUs. You will guide development so open-source AI agents operate locally, safely, and efficiently on consumer PCs, combining Nemotron models with privacy-focused runtimes.

The role requires deep expertise in Windows internals, LLM pipelines, and GPU acceleration.