Senior Power-Management Architect

7 Months ago • 3-10 Years

Job Summary

Job Description

Join a well-funded hardware startup in Silicon Valley as a Senior Power-Management Architect. Your role will involve defining, modeling, and optimizing power and performance features for cutting-edge RISC-V based Accelerated computing platforms. You will analyze power behavior of workloads, define and extend power management features to maximize performance under constraints, and integrate these heuristics into firmware and simulation models. Collaboration with FW, SW, and performance teams is key for driving platform development and ensuring features reach product quality. You will also prototype features, analyze benefits pre-silicon, and assist with post-silicon bringup.

Must have:

BS/MS degree in CS/CE/EE or equivalent
CPU/GPU/SoC power-management firmware architecture and coding
GPU/ML workload PnP analysis
Power-management feature definition (capping, thermal control, DVFS)
Ability to work collaboratively
Ability to initiate and drive tasks

Good to have:

Power and/or performance modeling using simulators

Perks:

Fun, creative, and flexible work environment

6 skills required

required for this role

Add these skills to join the top 1% applicants for this job

Job Details

Join a cutting-edge and well-funded hardware startup in Silicon Valley as a Senior Power-Management Architect, focused on defining, modeling and optimizing Power/Performance features on a cutting-edge design. Our mission is to reimagine silicon and create RISC-V based Accelerated computing platforms that will transform the industry. You will have the opportunity to work with some of the most talented and passionate engineers in the world to create designs that push the envelope on performance, energy efficiency and scalability. We offer a fun, creative and flexible work environment, with a shared vision to build products to change the world.

Responsibilities

As a Power Management Architect, you will own or participate in the following:
Work closely with the Performance team to analyze power behavior of workloads of interest on Rivos’ architecture
Work closely with the Performance team to analyze rack-level power and performance
Define and extend the power management features and heuristics, to maximize performance on workloads of interest under power and current constraints
Work closely with the FW and SW teams to integrate the heuristics into the FW code and simulation model. As well as rack-level power-optimization infrastructures
Work closely with the performance teams to help drive platform and system level PnP targeted framework development
Work closely with micro architecture and design teams to bring the new features to product level quality
Collaborate with the performance simulation teams to prototype the features and analyze their benefits pre-silicon
Assist with post-silicon bringup and characterization of the power-management architecture on RIvos’ devices.

Requirements

BS/MS degree in CS/CE/EE or equivalent experience
Experience with CPU/GPU/SoC power-management control firmware architecture and coding
Experience with GPU/ML workload PnP analysis at the system, server and rack level
Experience with the related power-management architecture feature definition such as power capping, thermal control, current capping, and DVFS
Good understanding of power and/or performance modeling using simulators is preferred
Ability to work collaboratively in a fast-paced and dynamic environment
Go-getter capable of initiating and driving tasks from start to finish with minimum technical oversight

Education and Experience

BS (5-10 years of experience) or MS (3-5 years of experience) with a degree in CS/CE/EE or equivalent field, The team already includes senior engineers who will collaborate on feature definition and mentoring.