Senior Engineer, Local AI - Agents and Systems

What you'll do

• Lead the development of agent frameworks natively on Windows environments.
• Build a technical roadmap for deploying self-evolving AI assistants on GeForce RTX hardware.
• Optimize agent runtimes specifically for Windows and consumer-grade GPU systems.
• Implement policy-based privacy and security frameworks for filesystem access and network egress.
• Develop secure inference routing and sandboxed execution environments for local AI models.
• Integrate open-source AI agents into the desktop ecosystem using advanced orchestration frameworks.
• Mentor other engineers and establish technical guidelines for AI agent deployment.
• Write production-ready code in C++ and Python to integrate systems with AI logic.

What we're looking for

• 10+ years of relevant professional software engineering experience.
• At least 3+ years in a Staff or Lead Architect role.
• BS, MS, or PhD in Computer Science, Computer Engineering, or a related technical field.
• Deep understanding of Windows OS internals, process isolation, sandboxing technologies, and system-level security architecture.
• Proven understanding of LLM inference pipelines, GPU-accelerated computing (CUDA, TensorRT), and running local models on consumer hardware.
• Practical experience with modern AI orchestration and agentic frameworks like OpenClaw, Hermes, or LangChain.
• Proficiency in C++ for performance-critical systems and Python for AI/blueprint logic.
• Experience building virtualization, containerization, or robust sandboxing tools natively for the Windows ecosystem.