Principal Architect, Performance Analysis and Modeling

The role

You will analyze machine learning workloads and create analytical models to project performance on d-matrix hardware. You will contribute hardware and software features to power next generation inference accelerators in datacenters.

What you will do

• Analyze the latest ML workloads including 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 research in ML architecture and algorithms
• Collaborate with Product, Hardware Design, Compiler, Inference Server, and Kernels teams
• Analyze properties of emerging machine learning algorithms and workloads and identify functional, performance implications
• Create analytical models to project performance on current and future generations of d-matrix hardware
• Propose new HW/SW features to enable or accelerate algorithms

Required qualifications

• BSEE with 10+ years of industry experience or MSEE with 8+ years of industry experience
• Solid grasp in multiple of the relevant areas, computer architecture, hardware-software codesign, performance modeling, ML fundamentals (particularly DNNs)
• Programming fluency in C/C++ or Python
• Experience with developing analytical performance models, architecture simulators for performance analysis
• Self-motivated team player with strong sense of collaboration and initiative

Nice to have

• MSEE preferred with 8+ years of industry experience
• Research background with publication record in top-tier architecture, or machine learning venues (such as ISCA, MICRO, ASPLOS, HPCA, DAC, MLSys etc.)

About the company

d-Matrix has pioneered a memory-centric architecture that brings compute directly into memory. The team works on chips, software, and rack-scale systems to tackle AI infrastructure challenges.