Hybrid Principal Software Engineer, Performance Modeling

d-Matrix; Seattle (WA); Hybrid; USD 175,000 - 285,000; Full time

Job summary

d-Matrix seeks a principal software engineer to analyze and model performance across the hardware/software boundary of AI inference accelerators. You will build analytical models for emerging workloads and extend simulators to guide HW/SW improvements, working closely with hardware design, compiler, inference server, and kernel teams.

You will contribute to modeling methodologies, stay current with ML architecture trends, and drive validation of assumptions through hands-on development in C/C++

Qualifications

• BS EE with 6+ years of industry experience or MS EE with 4+ years of industry experience.
• Strong knowledge of computer architecture, HW/SW co-design and performance modeling.
• Programming fluency in C/C++ or Python.
• Experience building analytical performance models or architecture simulators.
• Collaborative and able to work across hardware and software teams.

Responsibilities

• Analyze emerging ML workloads and model performance across hardware/software boundary.
• Build and maintain analytical performance models to project behavior on current/future hardware.
• Develop and extend architecture simulators to support performance analysis of HW/SW features.
• Collaborate with hardware design, compiler, inference server, kernel, and product teams to validate assumptions.
• Track ML architecture research and incorporate findings into modeling work.
• Propose HW/SW feature improvements based on modeling results.
• Document modeling methodology and findings for reuse.

Skills

C/C++

Python

Performance modeling

Architecture simulators

Team collaboration

Education

BSEE/BS in EE

MSEE

Tools

Analytical modeling tools

Simulation frameworks

Job description

d-Matrix seeks a principal software engineer to analyze and model performance across the hardware/software boundary of AI inference accelerators. You will build analytical models for emerging workloads and extend simulators to guide HW/SW improvements, working closely with hardware design, compiler, inference server, and kernel teams.

You will contribute to modeling methodologies, stay current with ML architecture trends, and drive validation of assumptions through hands-on development in C/C++