Principal AI Performance Architect & Modeling Lead

d-Matrix; Seattle (WA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

d-Matrix, headquartered in Santa Clara, CA, seeks a Principal Architect to accelerate AI application performance at hardware-software co-design frontier. You will analyze emerging ML workloads and contribute features for inference accelerators across datacenters, while staying current with ML architecture research and collaborating with Product, Hardware Design, Compiler, Inference Server, and Kernels.

Ideal candidates have deep expertise in computer architecture, performance modeling, and DNNs,

Qualifications

• BSEE with 10+ years of industry experience.
• Solid grasp through academic or industry experience in computer architecture, hardware-software co-design, performance modeling, ML fundamentals (DNNs).
• Programming fluency in C/C++ or Python.
• Experience with analytical performance models and architecture simulators.
• Research background with publications in top-tier venues is a plus.
• Self-motivated team player with collaboration and initiative.

Responsibilities

• Analyze the latest ML workloads (multi-modal LLMs, CoT reasoning models, video/audio generation).
• Contribute hardware and software features that power the next generation of inference accelerators in datacenters.
• Keep up with the latest ML architecture research and collaborate with Product, Hardware Design, Compiler, Inference Server, and Kernels.
• Create analytical models to project performance on current and future generations of d-Matrix hardware; propose HW/SW features to accelerate these algorithms.

Skills

C/C++

Python

Performance modeling

Architecture simulation

ML fundamentals

Team collaboration

Education

BSEE

MSEE

Job description

d-Matrix, headquartered in Santa Clara, CA, seeks a Principal Architect to accelerate AI application performance at hardware-software co-design frontier. You will analyze emerging ML workloads and contribute features for inference accelerators across datacenters, while staying current with ML architecture research and collaborating with Product, Hardware Design, Compiler, Inference Server, and Kernels.

Ideal candidates have deep expertise in computer architecture, performance modeling, and DNNs,