Principal AI Accelerator Architect

for section headings. Use

• for any list of duties/requirements/benefits. Use

  for prose. We need to decide which sections: About the role (prose), Responsibilities (list), Requirements (list), Qualifications (maybe combine with Requirements?), Skills (maybe separate?), Benefits (list), Pay (prose). The instruction: Prefer a few substantive sections over many thin ones. Could combine Requirements, Qualifications, Skills into one section? But they said use headings for those categories if content exists. We have content for Requirements (the "What We’re Looking For") and also "Particularly Relevant Experience" which could be Qualifications or Skills. Could split: Requirements (experience, understanding, track record, quantitative judgment, etc.) Qualifications (education, particularly relevant experience). Skills (maybe communication, collaboration). But to avoid many thin sections, we could combine into one "Requirements and Qualifications" but headings must be exactly those given? The instruction: use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It suggests we can use those headings if we have content. We can choose to include only those with real content. We have content for About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay. Schedule none. We need to decide what goes where. Let's map: About the role: introductory paragraphs describing company and role. Responsibilities: "What You’ll Do" list. Requirements: maybe the core requirements: 10+ years experience, deep understanding, track record, strong quantitative judgment, experience with models/tools, ability to reason across..., working knowledge of RTL..., experience collaborating..., strong communication, MS/PhD. Qualifications: "Particularly Relevant Experience" list. Skills: maybe the communication and collaboration skills? But those already in requirements. Could treat Skills as the "Strong written and verbal communication skills" etc. But we already have communication in requirements. Might be redundant. Perhaps we can put Skills as the "Ability to reason across workloads..." etc. But that's also in requirements. Given risk of thin sections, maybe combine Requirements and Qualifications into one section called "Requirements". But the instruction says we can use those headings; it's not mandatory to use all. It says "Use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It implies we can use those headings if appropriate. It doesn't say we must use each. So we could have sections: About the role, Responsibilities, Requirements, Benefits, Pay. And put qualifications/skills inside Requirements. But we have "Particularly Relevant Experience" which is definitely qualifications. Could be under Requirements as well. Thus we can have: - About the role (prose) - Responsibilities (ul) - Requirements (ul) combining the bullet lists from "What We’re Looking For" and "Particularly Relevant Experience" - Benefits (ul) from "Why Join Cerebras" - Pay (prose) salary range. We must not include Schedule. Now we need to ensure we preserve all substantive info. Let's extract all prose bits. About the role prose: combine the introductory paragraphs up to "You will own architectural features from initial insight through a well-grounded proposal that is ready for implementation." Also maybe include the sentence "Principal AI Accelerator Architect Our architecture removes many of the constraints..." Actually that's part of role description. Let's capture: "Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation. Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference. Principal AI Accelerator Architect Our architecture removes many of the constraints imposed by conventional collections of packaged processors and creates a fundamentally different design space spanning compute, memory, communication, programmability and system scaling. We are looking for an experienced architect to conceive and drive new capabilities for our next-generation AI accelerators. This is an end-to-end architecture role: you will identify opportunities from important AI workloads, quantify their performance and efficiency value, develop the microarchitecture and establish implementation feasibility across hardware and software. You will own architectural features from initial insight through a well-grounded proposal that is ready for implementation." We need to ensure no duplication. Responsibilities list: as above. Requirements list: combine: From "What We’re Looking For": - 10+ years of experience in computer architecture, microarchitecture or processor development, including work with CPUs, GPUs, AI accelerators or other high-performance processors. - Deep understanding of computer architecture and microarchitecture. - A track record of taking architectural features from workload need or initial concept through microarchitecture definition and implementation. - Strong quantitative judgment, including the ability to evaluate performance benefits against power, area, complexity and programmability costs. - Experience using targeted hardware performance models and architecture-exploration tools to evaluate specific features, using Python, C++ or similar environments. - Ability to reason across workloads, kernels, memory systems, interconnects and compute pipelines. - Working knowledge of RTL, synthesis, timing, power and physical-design considerations sufficient to establish implementation feasibility. - Experience collaborating closely with RTL, verification, physical-design, compiler, kernel and system-software teams. - Strong written and verbal communication skills, including the ability to make and defend consequential architectural decisions. - MS or PhD in Electrical Engineering, Computer Engineering, Computer Science or equivalent practical experience. From "Particularly Relevant Experience": - Architecture or microarchitecture development for machine-learning accelerators, GPUs, CPUs, vector processors or network processors. - Transformer inference or training, including attention, matrix and vector operations, collectives, sparsity, quantization or mixture-of-experts workloads. - Memory hierarchy, on-chip networks, DMA engines, distributed compute