Senior Staff AI Accelerator Performance Architect
Cerebras Systems, Inc. · Sunnyvale, CA ·
- Work mode
- Onsite
- Seniority
- Staff
- Category
- Architecture
- Experience
- 7+ years
Cerebras is hiring a Senior Staff AI Accelerator Performance Architect in Sunnyvale, CA to develop performance models for AI accelerator and system architectures, analyze AI workloads from kernels to end-to-end execution, and identify hardware/software bottlenecks — validating models against RTL, emulation, and silicon measurements to inform architecture and product decisions.
You will develop performance models for accelerator and system architectures, analyze AI workloads, and identify hardware and software bottlenecks. You will evaluate architectural features, validate models against RTL, emulation, and silicon measurements, and translate findings into recommendations for architecture and product decisions.
Responsibilities
- Develop and evolve performance models and modeling methodologies
- Analyze AI workloads from kernels to end-to-end execution
- Identify hardware and software bottlenecks
- Evaluate architectural features and quantify performance improvements
- Develop workload projections and competitive performance analyses
- Validate models against RTL, emulation, and silicon measurements
- Define representative workloads and performance targets
Requirements
- 7+ years of performance analysis, modeling, or architecture exploration experience
- Hardware architecture knowledge
- Performance modeling with Python, C++, or similar environments
- Knowledge of processor architecture, memory systems, interconnects, and parallel execution
- Workload profiling and quantitative validation
- MS or PhD in Electrical Engineering, Computer Engineering, Computer Science, or equivalent practical experience
Benefits
- Bonus
- Equity