Lead Engineer: Local AI Agents on Windows & GPUs

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 356,500; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA Corporation in Santa Clara, CA, seeks a Senior Engineer to lead the deployment of local AI agent frameworks and runtimes on Windows and GeForce RTX GPUs. You will guide OSS agents (such as OpenClaw) to run locally, safely, and efficiently on consumer PCs.

You will own the Windows-focused roadmap, mentor engineers, and collaborate with AI research and driver teams to ensure privacy and security policies guide file access, inference routing, and network egress.

Qualifications

• 10+ years of professional software engineering experience with leadership roles.
• Deep understanding of Windows OS internals, sandboxing, and system security.
• Experience with LLM inference pipelines and local models on consumer hardware.
• Familiarity with OpenClaw, Hermes, LangChain and multi-agent orchestration.
• Proficient in C++ and Python; comfortable with OS integration and performance tuning.
• Experience building virtualization, containers, or sandboxing tools for Windows.

Responsibilities

• Lead development of agent frameworks natively on Windows environments.
• Create roadmaps to bring always-on, self-evolving AI assistants to GeForce RTX PCs.
• Optimize agent runtimes and enforce policy-based privacy and security.
• Collaborate with AI research, driver teams, and OpenClaw community.
• Mentor engineers and establish production-ready code standards.

Skills

C++

Python

Multi-agent systems

LLM inference pipelines

Education

BS/MS/PhD in CS/CE or related field

Tools

OpenClaw

Hermes

LangChain

Ollama

Llama.cpp

vLLM

CUDA

TensorRT

Job description

NVIDIA Corporation in Santa Clara, CA, seeks a Senior Engineer to lead the deployment of local AI agent frameworks and runtimes on Windows and GeForce RTX GPUs. You will guide OSS agents (such as OpenClaw) to run locally, safely, and efficiently on consumer PCs.

You will own the Windows-focused roadmap, mentor engineers, and collaborate with AI research and driver teams to ensure privacy and security policies guide file access, inference routing, and network egress.