Senior AI Systems Performance Architect

Socket.dev; Sunnyvale (CA); On-site; USD 175,000 - 275,000; Full time

Job summary

Cerebras Systems is seeking a Senior Staff AI Accelerator Performance Architect to guide next-generation AI systems. You will connect real workloads to architectural behavior, identify bottlenecks, quantify improvements and influence roadmaps through rigorous performance analysis.

This role requires deep hardware/architecture knowledge and experience across kernels, runtimes and system performance. The base salary range is $175,000 to $275,000 per year, with possible bonus and equity.

Qualifications

• 7+ years of experience in performance analysis or architecture exploration for CPUs, GPUs, AI accelerators or high-performance systems.
• Strong understanding of hardware architecture from hardware, compiler, kernel, runtime or system-performance work.
• Experience developing analytical, simulation-based or trace-driven models using Python, C++ or similar environments.
• Solid understanding of processor architecture, memory systems and interconnects.

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 kernels to end-to-end inference and training to determine time, bandwidth, compute and capacity usage.
• Identify hardware and software bottlenecks and quantify opportunities to improve latency, throughput, utilization and energy efficiency.
• Evaluate proposed architectural features and determine their performance return across workloads.
• Study how models and kernels map onto the compute, memory and communication architecture.
• Collaborate with architecture, compiler, kernel, runtime and systems teams to evaluate mappings and optimizations.
• Develop workload projections and competitive performance analyses with transparent assumptions.
• Create concise recommendations translating results into architectural and product decisions.
• Improve modeling methodology, validation and correlation with RTL, emulation and silicon measurements.
• Help define representative workloads, performance targets and success criteria for future products.

Skills

Performance analysis

Architecture exploration

Python

C++

Hardware architecture

End-to-end performance

Education

MS or PhD in Electrical/Computer Engineering or CS

Tools

RTL simulation

Emulation

Job description

Cerebras Systems is seeking a Senior Staff AI Accelerator Performance Architect to guide next-generation AI systems. You will connect real workloads to architectural behavior, identify bottlenecks, quantify improvements and influence roadmaps through rigorous performance analysis.

This role requires deep hardware/architecture knowledge and experience across kernels, runtimes and system performance. The base salary range is $175,000 to $275,000 per year, with possible bonus and equity.