AI Runtime & ML Systems Engineer: Inference & Deployment

HP Inc.; Austin (TX); On-site; USD 131,000 - 205,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Disability insurance

Employee assistance program

Flexible spending account

Life insurance

Generous time off and parental leave

11 paid holidays

Flexible vacation and sick leave

Job summary

HP, Inc. is seeking an AI Runtime / ML Model Systems Engineer to design and implement runtime abstractions and intelligent model placement across heterogeneous compute resources.

The role emphasizes secure, scalable software engineering with leadership over vendor activities and POC execution. The position is based in Houston with a 4-days-per-week in-office requirement, offering a competitive compensation package and benefits.

Qualifications

• Four-year or graduate degree in CS/IT/SE or equivalent experience.
• Typically 7–10 years in software design, architecture or related field.
• Strong AI runtime expertise required.
• Experience with optimizing inference execution is preferred.

Responsibilities

• Build runtime abstraction frameworks.
• Implement model placement policies.
• Develop xPU routing logic.
• Optimize inference execution.
• Lead the building of software projects aligned with security strategies.
• Create standards, designs and automate deployment of software.
• Design and develop solutions that protect software and data.
• Contribute to technology strategy and roadmaps; run POCs.
• Supervise external engineering vendors and provide feedback.

Skills

Agile Methodology

API

Automation

C++

Java

JavaScript

Kubernetes

Microservices

Python

React.js

SQL

DevOps

AWS

Microsoft Azure

Education

Four-year or Graduate Degree in Computer Science, Information Technology, Software Engineering, or related discipline

Tools

ONNX

TensorRT

OpenVINO

Docker (Software)

NPU/GPU scheduling

Job description

HP, Inc. is seeking an AI Runtime / ML Model Systems Engineer to design and implement runtime abstractions and intelligent model placement across heterogeneous compute resources.

The role emphasizes secure, scalable software engineering with leadership over vendor activities and POC execution. The position is based in Houston with a 4-days-per-week in-office requirement, offering a competitive compensation package and benefits.