Description

Amazon Web Services provides a highly reliable, scalable, low-cost cloud infrastructure platform that powers hundreds of thousands of businesses in 190+ countries around the world. We have data center locations in the U.S., Europe, and Asia, and customers across all industries. We are seeking experienced System-on-Chip (SoC) Power Analysis Engineers to build the next generation of our cloud server infrastructure. Our success depends on our world-class server infrastructure; we're handling massive scale and rapid integration of emergent technologies.

As a member of the Cloud-Scale Machine Learning Acceleration team you'll be responsible for the entire SoC power rollup, performing power analysis at various stages of the design, and developing power optimization techniques from SoC to complete system. These systems include accelerators such as AWS Inferentia and AWS Trainium which are machine learning products designed to deliver high performance at low cost.

You’ll provide leadership in the application of new technologies to large scale deployments in a continuous effort to deliver a world-class customer experience. This is a fast-paced, intellectually challenging position, and you’ll work with thought-leaders in multiple technology areas. You’ll have high standards for yourself and everyone you work with, and you’ll be constantly looking for ways to improve our products' performance, quality and cost. We’re changing an industry, and we want individuals who are ready for this challenge and want to reach beyond what is possible today.

Key job responsibilities

• Define new tests, test benches that can isolate power inefficiencies.

• Work with the verification team in defining and developing test cases to measure power and drive power optimization for active and idle use cases

• Familiarity with modern SoC power delivery; power state management, power tradeoffs, throttling techniques, thermal constraints, etc.

• Set power targets for entire SoC and drive power convergence for all IPs across the SOC

• Assess power impact of new technology nodes and make recommendations for optimal voltage and frequency points for all IPs.

• Work with Silicon and power measurement teams to debug power issues and correlate silicon data with power model.

• Work with system and test teams and provide guidance for voltage rail selection sizing, power up sequencing, board and package design considerations, binning and yield

• Power characterization and shmooing post silicon validation

• Thermal / Power shmooing

• di/dt measurement and validation for Core vdd and other IO’s

-Scripting and test automation

Basic Qualifications

• BS degree or higher in EE or CE

• 3+ years or more of SoC development experience

• Knowledge of power savings techniques and experience with optimizing SoCs to lower power dissipation

• Experience running and expertise of sign-off power analysis tools

• Experience running and debugging Verilog RTL and gate level simulations

• Must be proficient with TCL scripting

• Must work well with others on cross-functional teams and must be able to multi-task

Preferred Qualifications

• Experience using lab equipment for silicon validation

• Experience analyzing power for high power chips desired

• Proficient writing other scripting languages such as Python or Perl

• Experience with electro-migration, IR drop, power integrity, thermal analysis is desired

• General knowledge of Machine Learning, Computer Arithmetic, Server/Datacenter Architecture

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.