Senior Power Architect, Annapurna Labs, ML Acceleration Power Architecture

Description

AWS Utility Computing (UC) provides product Annapurna Labs (our organization within AWS UC) designs silicon and software that accelerates innovation. Customers choose us to create cloud solutions that solve challenges that were unimaginable a short time ago—even yesterday. Our custom chips, accelerators, and software stacks enable us to take on technical challenges that have never been seen before, and deliver results that help our customers change the world.

We are seeking an experienced Power Architect to join our Machine Learning Acceleration team. In this role, you will be responsible for developing and implementing power architecture solutions, optimizing power consumption, and managing thermal constraints for ML accelerator designs in Amazon data centers. You will work closely with cross-functional teams to deliver innovative power management solutions that maximize performance while maintaining power efficiency.

• Design and implement comprehensive power architecture solutions for ML accelerator platforms
• Develop and optimize DVFS (Dynamic Voltage and Frequency Scaling) flows and power control schemes
• Create and validate power management algorithms for various operating conditions
• Lead peak power management initiatives and develop solutions for di/dt handling
• Analyze and optimize workloads for optimal power-performance trade‑offs
• Drive cross‑functional collaboration with software teams to develop, integrate and verify power management solutions across the hardware‑software stack
• Collaborate with RTL and pre‑silicon teams to ensure power requirements are met throughout the design flow
• Create power models and develop automation scripts for power analysis
• Provide technical leadership and mentoring to team members
• Partner with cross‑functional teams to drive power architecture requirements and solutions

• Bachelor's degree in Electrical Engineering, Computer Engineering, or a related technical field
• 3+ years of experience in power architecture and management
• Strong background in DVFS flows and power optimization techniques
• Proven experience in designing power control schemes and algorithms
• Demonstrated expertise in peak power management and di/dt handling
• Proficiency in Python programming for scripting and modeling
• Experience with workload optimization for power and performance
• Working knowledge of C/C++ programming and software development lifecycle
• Understanding of RTL design and pre‑silicon validation flow
• Strong analytical and problem‑solving skills

• Master's degree or equivalent
• 10+ years of experience in power architecture for high‑performance computing systems
• Experience with machine learning accelerator architectures
• Track record of leading complex technical projects
• Experience with power modeling and analysis tools
• Published papers or patents in power architecture or related fields
• Strong leadership skills with demonstrated ability to take ownership of complex projects, deliver results in a fast‑paced environment, and drive customer‑focused solutions
• Experience with data center power management solutions
• Knowledge of industry standards and specifications related to power management
• Excellent communication and presentation skills

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Job : A3113531 – Annapurna Labs (U.S.) Inc.