Senior Staff AI Accelerator Performance Architect

About the role

Cerebras builds wafer-scale AI chips, 56 times larger than GPUs, delivering training and inference speeds over 10 times faster than GPU-based cloud services. It is looking for a Senior Staff AI Accelerator Performance Architect to guide the evolution of its next-generation AI systems. The role connects real workloads to architectural behavior, identifies bottlenecks, quantifies improvement opportunities and influences hardware and software roadmaps through rigorous performance analysis. It is a performance and architecture role, not a production RTL-design position.

Key responsibilities

• Own and evolve performance models and modeling methodologies for next-generation accelerator and system architectures.
• Build and extend analytical, simulation-based or trace-driven models across workloads, architectural features and product generations.
• Analyze AI workloads from individual kernels through end-to-end inference and training to see where time, bandwidth, compute and capacity are spent.
• Identify hardware and software bottlenecks and quantify opportunities to improve latency, throughput, utilization and energy efficiency.
• Evaluate proposed architectural features and their expected performance return across representative workloads.
• Study how models and kernels map onto compute, memory and communication architecture, and partner with architecture, compiler, kernel, runtime and systems teams on mappings and optimizations.
• Develop workload projections and competitive performance analyses, and turn performance results into clear architectural and product recommendations.
• Improve modeling methodology and validate it against RTL, emulation and silicon measurements; help define representative workloads, performance targets and success criteria.

Required profile

• 7+ years of experience in performance analysis, performance modeling or architecture exploration for CPUs, GPUs, AI accelerators or other high-performance computing systems.
• Strong understanding of hardware architecture from hardware, compiler, kernel, runtime or system-performance work.
• MS or PhD in Electrical Engineering, Computer Engineering, Computer Science or equivalent practical experience.
• Ability to move between kernel-level behavior and end-to-end application or system performance, and to communicate assumptions, uncertainties and recommendations clearly.

Required skills

• Experience developing analytical, simulation-based or trace-driven performance models in Python, C++ or similar environments.
• Solid understanding of processor architecture, memory systems, interconnects, parallel execution and hardware resource constraints.
• Experience profiling workloads, forming performance hypotheses and validating them quantitatively.
• Understanding of how software mapping and programmability affect hardware performance.
• Potentially relevant: transformer inference or training analysis, GEMM/GEMV, collective communication, quantization, kernel optimization, RTL simulation, FPGA prototypes, competitive AI accelerator analysis.

The base salary range is $175,000 to $275,000 annually, with possible bonus and equity.