AI Performance & Benchmark Engineer

Hp Iq; Houston (TX); On-site; USD 131,000 - 205,000; Full time

Benefits offered by this job

Health insurance

Vision insurance

Disability insurance

Employee assistance program

Flexible spending account

Life insurance

Paid holidays

Job summary

HP is seeking a Systems Evaluation Engineer to assess AI software performance and customer impact. You will design evaluation methodologies, benchmark AI workloads, and interpret results to guide product decisions.

Strong skills in Python/C++, ONNX/GGUF, and system-level performance are essential. You'll collaborate with product, architecture, and engineering teams to ensure scalable, measurable outcomes and provide actionable feedback.

Qualifications

• 7+ years in systems evaluation, performance engineering or related field.
• Strong understanding of AI inference workloads and model execution.
• Experience designing benchmarking methodologies and metrics.
• Familiarity with ONNX and GGUF and related execution approaches.
• Knowledge of system-level performance, memory, concurrency, OS interactions.
• Proficient in Python or C++ with automation experience.

Responsibilities

• Translate user stories and customer experiences into measurable success criteria.
• Design repeatable benchmarking frameworks for AI workloads.
• Compare model formats, runners, and hardware configurations with controlled measurements.
• Analyze inference behavior, latency, memory, and token generation metrics.
• Assess system responsiveness under single and concurrent AI workloads.
• Provide actionable feedback linking findings to customer impact.
• Develop automation and reporting tools for reproducible evaluations.
• Present performance trends and trade-offs in technical reviews.

Skills

AI systems

Systems evaluation

Benchmarking

Python

C++

Data analysis

Project communication

Education

Bachelor's degree in computer science, statistics, software engineering, or related field

Tools

ONNX

GGUF

Model runners

Python tooling

C++

Job description

HP is seeking a Systems Evaluation Engineer to assess AI software performance and customer impact. You will design evaluation methodologies, benchmark AI workloads, and interpret results to guide product decisions.

Strong skills in Python/C++, ONNX/GGUF, and system-level performance are essential. You'll collaborate with product, architecture, and engineering teams to ensure scalable, measurable outcomes and provide actionable feedback.