Principal AI Performance Architect & Modeling

Entrada Ventures; Santa Clara (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

d-Matrix is seeking a Principal Software Engineer to lead performance analysis across hardware/software boundaries of AI inference accelerators. You will build analytical models and simulators, collaborate with Hardware Design, Compiler, Inference Server, and Kernels teams to project performance for current and future silicon.

The role emphasizes modeling workloads such as generative inference, multi-modal LLMs, and CoT reasoning, with hands-on development in C/C++ or Python, and strong

Qualifications

• BS EE or MS EE with relevant industry experience.
• Strong knowledge of computer architecture and ML fundamentals.
• Experience with performance modeling and simulation tools.

Responsibilities

• Analyze emerging ML workloads and hardware/software interactions.
• Build and maintain analytical models projecting behavior of accelerators.
• Develop/extend architecture simulators for performance analysis.
• Collaborate with hardware design, compiler, inference server, kernel, and product teams.
• Track ML architecture research and incorporate findings into modeling work.
• Suggest HW/SW improvements based on modeling results.

Skills

Computer architecture

HW/SW co-design

Performance modeling

ML fundamentals

C/C++

Python

Education

BSEE with 6+ years

MSEE with 4+ years

Tools

Analytical performance models

Architecture simulators

Job description

d-Matrix is seeking a Principal Software Engineer to lead performance analysis across hardware/software boundaries of AI inference accelerators. You will build analytical models and simulators, collaborate with Hardware Design, Compiler, Inference Server, and Kernels teams to project performance for current and future silicon.

The role emphasizes modeling workloads such as generative inference, multi-modal LLMs, and CoT reasoning, with hands-on development in C/C++ or Python, and strong