AI Performance Simulation Architect
$100,000–$500,000 year
Remote · United States or US
Job Summary
Architect and build scalable cycle-accurate AI accelerator performance models spanning accelerators, NoCs, and memory hierarchies to inform the design of future hardware platforms; define abstraction layers from high-level analytical models to detailed simulations (e.g., GEM5 or SST); lead performance modeling and bottleneck analysis to guide architectural and system optimization; integrate the AI accelerator performance model into a larger heterogeneous simulation environment to evaluate system performance; require deep experience with parallel programming (OpenMP, MPI, CUDA, OpenCL) and system analysis tools, and collaborate across hardware, software, and research domains.
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.