Principal Architect Performance Analysis and Modeling
Core
Analyze ML workloads and create analytical models to project performance on current and future generations of d-Matrix hardware, proposing new HW/SW features to accelerate algorithms.
Role type
Principal Architect, Performance Analysis and Modeling
Builds
Next generation of inference accelerators in datacenters
Domain
AI hardware acceleration, computer architecture, machine learning
Deliverable
production ML models
Required skills
Computer architecture, hardware software codesign, performance modeling, ML fundamentals (DNNs), C/C++ or Python programming, analytical performance model development, architecture simulators
Preferred skills
Research background with publications in top-tier architecture or ML venues (ISCA, MICRO, ASPLOS, HPCA, DAC, MLSys)
Technologies
DIMC, D2D, 3D-DRAM, tensor cores, inference servers, compilers, kernels
Responsibilities
Analyze properties of emerging machine learning algorithms and workloads to identify functional and 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
Seniority
Principal, hands-on IC with strategy & mentorship
