Amazon Power Characterization Engineer Annapurna Labs 

United States, Texas, Austin 

607971875

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.- 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- 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

- 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

- 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