Agentic AI AI Runtime / ML Model Systems Engineer

Location: Spring, Texas, United States of America; Houston in-office requirement 4 days per week. Travel up to 25%.

Salary: $130,700–$205,200 USD annually, with additional bonus and/or equity opportunities for U.S. candidates.

Company

hirify.global develops software, technology products, and services for business and consumer use.

What you will do

• Build runtime abstraction frameworks across heterogeneous compute resources.
• Implement intelligent model placement policies and xPU routing logic.
• Optimize inference execution and support edge AI deployment.
• Lead software development projects, platforms, standards, and automated deployment solutions.
• Design solutions that protect and manage software products and data.
• Supervise external engineering vendors and review their testing work.

Requirements

• 7–10 years of experience in software design and development, architecture, programming, or a related field.
• Strong AI runtime expertise and experience optimizing inference execution.
• Experience with ONNX, TensorRT, OpenVINO, NPU/GPU scheduling, and edge AI deployment.
• Four-year or graduate degree in computer science, information technology, software engineering, or a related discipline, or equivalent demonstrated experience.
• Knowledge of C++, Python, Java, JavaScript, APIs, Docker, Kubernetes, microservices, DevOps, cloud platforms, and scalable software engineering.
• Must work in the Houston office 4 days per week.

Culture & Benefits

• Full-time employment with health, dental, and vision insurance.
• Short- and long-term disability, life insurance, employee assistance, and flexible spending accounts.
• 4–12 weeks of fully paid parental leave based on tenure.
• 11 paid holidays plus flexible paid vacation and sick leave.
• Bonus and/or equity opportunities may apply to U.S. candidates.