Power Engineering Architect
CerebrasJob Title
Power Engineering Architect
Role Summary
Lead the product power roadmap and drive power delivery architecture for high-performance compute, AI/ML accelerators and advanced ASIC platforms. Own system-level power delivery strategy, collaborate with ASIC, package, PCB, mechanical and product teams, and move solutions from concept through production.
This role is technically deep and execution-oriented, focused on enabling ultra-high current density and efficient thermal designs for data center accelerator systems.
Experience Level
Senior — 15+ years of hands-on experience in power delivery systems and related hardware development.
Responsibilities
Ownership and technical leadership for system power delivery and thermal solutions across product development.
- Lead system architecture exploration focused on power delivery and thermal management for AI accelerators.
- Define and drive vertical power delivery approaches to the wafer to enable ultra-high current density.
- Collaborate with product, ASIC, package, PCB, and mechanical teams to specify and validate power requirements.
- Architect power delivery systems optimized for electrical performance and cooling efficiency.
- Evaluate architectures and select strategic partners/vendors for technology development.
- Oversee solutions through full lifecycle: concept, design, validation, and production deployment.
- Coordinate cross-discipline trade-offs among silicon, package PDN, and thermal subsystems.
Requirements
Key must-have technical skills and domain experience. Preferred items are listed separately.
- Must-have:
- 15+ years of hands-on experience in power delivery systems for server or accelerator platforms.
- Proven practical experience in thermal modeling and implementing cooling solutions.
- Deep experience with high-current, low-voltage power delivery for advanced silicon.
- Experience with multiphase buck regulators, digital power controllers, DrMOS, smart power stages, and integrated voltage regulators.
- Familiarity with server hardware, AI accelerators, datacenter platforms, GPUs/CPUs/TPUs, or similar enterprise products.
- Strong interpersonal and cross-functional collaboration skills.
- Nice-to-have / Preferred:
- Experience developing advanced power modules with optimized thermal and magnetic characteristics.
- Background in semiconductor power technologies such as PMICs and integrated power modules.
- Experience with package PDN design, power vias, bumps, interposers, substrates, and ASIC power delivery structures.
- Expertise in power architecture for chiplet-based designs, IVRs, and 2.5D/3D integration.
Education Requirements
M.S. in Electrical Engineering (MSEE) or Computer Engineering (MSCE) required; Ph.D. preferred. Equivalent industry experience is acceptable where noted.
About the Company
Company: Cerebras
Headquarters: Sunnyvale, CA, USA
Developer of wafer-scale AI accelerators, Cerebras designs the Wafer Scale Engine (WSE)—one of the world’s largest AI chips—to deliver high-speed training and inference solutions for model labs, enterprises, and AI-native startups.
