Software Engineer (AI)

TL;DR

Software Engineer (AI): Lead integration and implementation of Small Language Model inferencing on Windows laptops and desktops with an accent on runtime performance optimization, security, and system-level programming. Focus on designing core agent runtimes, embedding safety features, and collaborating with cross-functional teams to deliver production-ready AI solutions.

Location: Onsite in Morrisville, North Carolina, United States

Company

hirify.global is a global technology powerhouse with a broad AI-enabled product portfolio, driving innovation in AI systems and infrastructure worldwide.

What you will do

• Design, implement, and maintain core agent runtimes for dynamic model management and inference scheduling.
• Develop system integrations between Windows applications and AI runtime components.
• Implement security and privacy controls including sandboxing and audit logging.
• Optimize runtime performance across heterogeneous compute platforms and AI frameworks.
• Embed safety, telemetry, and interpretability features into AI systems.
• Collaborate with AI researchers, product managers, QA, and DevOps teams; mentor junior engineers.

Requirements

• Must be located in or able to work onsite in Morrisville, North Carolina, USA
• Expertise in Windows development including Win32 APIs and system-level programming.
• Experience with GGML, GGUF, llama.cpp, ONNX, OpenVino, RyzenAI, and QNN runtimes.
• Proficiency in C/C++ and working knowledge of Python and PyTorch.
• Strong problem-solving and debugging skills in multi-threaded environments.
• Knowledge of Windows software security best practices.

Nice to have

• Experience with Kotlin Multiplatform or other cross-platform frameworks.
• Contributions to open-source AI runtimes or Windows utilities.
• Background in performance optimization, compiler toolchains, or hardware acceleration.