Lead Architect, Windows AI Agent Frameworks

Jobtailor; California (MO); On-site; USD 180,000 - 240,000; Full time

Job summary

Jobtailor is seeking a Lead Engineer to head the development of native Windows agent frameworks and scalable AI assistants. You will chart the technical roadmap for always-on, self-evolving AI agents on GeForce RTX PCs, while optimizing runtimes and ensuring robust security policies.

The role requires deep expertise in Windows internals, LLM pipelines, and GPU-accelerated computing, with a track record of mentoring teams and delivering production-grade code.

Qualifications

• BS in Computer Science, MS in Computer Engineering, or PhD in related field
• Deep understanding of Windows OS internals, process isolation, sandboxing, and security architecture
• Proven experience with LLM inference pipelines and GPU-accelerated computing on consumer-grade hardware
• Practical experience with AI orchestration and agentic frameworks (OpenClaw, Hermes, LangChain)
• Proficiency in C++ for performance-critical systems and Python for AI/blueprint logic
• Experience building virtualization, containerization, or robust sandboxing tools for Windows

Responsibilities

• Lead engineering efforts to develop agent frameworks natively on Windows
• Build the technical roadmap to bring always-on, self-evolving AI assistants to GeForce RTX PCs and laptops
• Mentor engineers and deliver production-ready code while ensuring privacy and security compliance

Skills

Windows OS Internals

C++ Proficiency

Python Proficiency

LLM Inference Pipelines

AI Orchestration Frameworks

Agent Framework Development

GPU-Accelerated Computing

System-Level Security Architecture

Process Isolation

Virtualization Tools

Containerization Tools

Mentoring

Collaboration

Leadership

Education

BS in Computer Science

MS in Computer Engineering

PhD in Related Field

Tools

CUDA

TensorRT

OpenClaw

Hermes

LangChain

Job description

Jobtailor is seeking a Lead Engineer to head the development of native Windows agent frameworks and scalable AI assistants. You will chart the technical roadmap for always-on, self-evolving AI agents on GeForce RTX PCs, while optimizing runtimes and ensuring robust security policies.

The role requires deep expertise in Windows internals, LLM pipelines, and GPU-accelerated computing, with a track record of mentoring teams and delivering production-grade code.