ASIC Architect

Responsibilities

• Translate high-level architecture specifications into micro-architecture feature requirements
• Bring up new features in the performance and power models
• Perform comprehensive PPA (Power, Performance, Area) trade-offs for new architectural features
• Extract insights for new features and micro-architecture power efficiency
• Profile workloads, identify bottlenecks, and project competitor performance for benchmarking
• Engage with software teams for end-to-end application level modeling at the cluster level
• Identify opportunities for kernel-level hardware acceleration

Requirements

• Masters or PhD in Electrical or Computer Engineering
• 10+ years of experience in performance analysis and modeling across GPUs, CPUs, or accelerator products
• Strong background in computer architecture and high-level architectural trade-offs
• Proficiency in Python or similar analytical environments for standing up new performance models from scratch
• Exposure to micro-code (kernel) performance bottlenecks and optimization techniques

Preferred Qualifications

• Good understanding of how high-level workloads map to underlying micro-architecture
• Understanding of basic ML workload profiling techniques and model network architecture

About the Company

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. Our novel wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, empowering machine learning users to effortlessly run large-scale ML applications. Our technology is transforming the industry, offering the fastest Generative AI inference solution in the world.