Principal AI Accelerator Architect

43 minutes agoHeadSalary: 200K - 300KSunnyvale, USA Onsite Full Time Engineering Jobs by Cerebras Systems, Inc.

Cerebras Systems, Inc.

Cerebras builds wafer-scale AI computing systems and a cloud inference platform for training, fine-tuning, and serving AI models.

Series F+Recently fundedCompany intelligence

Sunnyvale, California, United States

Funding history

Initial Public Offering ($6.4B)Revolving credit facilitySeries H ($1B)

Investors

Moore Strategic Ventures Valor Equity Partners Coatue Alpha Wave Global AMD

About Cerebras Systems, Inc.

Cerebras Systems is an AI-infrastructure company founded in 2015. It sells rack-scale wafer-scale computing systems and provides cloud-based, API-accessible AI inference alongside on-premises deployments.

View jobs by Cerebras Systems, Inc.

Skills

Ai Accelerator C#Compiler Computer Architecture Dma Inference Interconnect Kernel Memory Microarchitecture Performance Modeling Physical Design Python Quantization Rtl Synthesis Timing Training Transformer

Candidate Availability

Onsite · Sunnyvale · Required

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will analyze AI workloads and bottlenecks, quantify architectural opportunities, and translate them into microarchitecture. You will develop feasibility experiments, evaluate trade-offs, write specifications, lead technical reviews, and partner with implementation teams through handoff and development.

Requirements

10+ years of computer architecture, microarchitecture, or processor-development experience
Deep computer-architecture and microarchitecture knowledge
Experience taking architectural features through definition and implementation
Performance, power, area, complexity, and programmability trade-off analysis
Hardware performance-modeling or architecture-exploration experience using Python, C++, or similar environments
Knowledge of workloads, kernels, memory systems, interconnects, and compute pipelines
Working knowledge of RTL, synthesis, timing, power, and physical design
Experience collaborating with RTL, verification, physical-design, compiler, kernel, and system-software teams
MS or PhD in Electrical Engineering, Computer Engineering, Computer Science, or equivalent practical experience

Responsibilities

Analyze AI workloads, kernels, and system bottlenecks
Quantify feature value with performance models and workload studies
Translate architectural ideas into microarchitecture
Evaluate compiler, runtime, programming-model, and kernel interactions
Develop feasibility prototypes, RTL experiments, synthesis studies, or analytical models
Explore architectural alternatives and articulate trade-offs
Write architecture and microarchitecture specifications
Lead cross-functional technical reviews and implementation handoffs
Partner with implementation teams to preserve architectural intent and resolve issues

Benefits

Bonus
Equity