3 days ago

Power Management Architecture and Performance Modeling Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 8 hours agoStatus: Live

Job Summary

Contribute to power-constrained performance modeling for AMD Instinct AI/ML/HPC GPUs, supporting Perf@Power attainment from pre-Si concept-exit through post-Si product launch. Define firmware-based and multi-level power management architecture (from micro-architecture to datacenter orchestration), develop performance/power models with trade-off analysis, and build ML-based modeling to improve prediction accuracy and speed. Collaborate cross-functionally to validate, correlate, and drive power efficiency improvements.

Location: Markham

Workplace: Onsite

Employment Type: Full time

Job Function: Architecture & Urban Planning

Key Responsibilities

•Support power-constrained performance modeling, projections, target setting, and attainment tracking from concept-exit (pre-Si) to product launch (post-Si) for AMD Instinct accelerators.
•Contribute to defining power management architecture features across firmware, AVFS, micro-/macro-architecture, SoC, rack, and datacenter levels.
•Develop and maintain power and performance models for Cdyn/Leakage/STA/Area trade-off analysis and attainment.
•Create ML-based modeling solutions to improve accuracy, speed, and scalability of power/performance prediction and automate pre-Si/post-Si correlation.
•Collaborate cross-functionally to support P&P attainment, perform power/performance roll-ups, and support post-Si debug and calibration of pre-Si models.

Key Requirements

•Background in computer architecture, processor/accelerator development, or power management architecture.
•Experience or strong interest in firmware-based power management, AVFS technologies, and power features across micro-architecture, macro-architecture, SoC, rack, and datacenter levels.
•Experience or strong interest in power/performance projections, modeling, and optimization at the SoC or system level.
•Familiarity with digital logic physical design and power management techniques such as clock gating, power gating, V-F curves, p-states, and on-die voltage regulation.
•Good communication skills and ability to collaborate effectively with engineering teams.

Experience:AI/MLHPCGPUsDatacenterEmbedded systems

Education:Bachelor's in Computer Science, Computer Engineering, Electrical Engineering, or related field

Skills:Analytical skillsCommunicationCollaboration

Languages:En-us

Tech Stack:Power management modelingPre-SiPost-SiPerf@PowerSMU-driven power/thermal controlPower state managementAVFSRTAVFSClock gatingPower gatingDynamic voltage/frequency scalingP-statesPower domainsPower delivery partitioningOn-die voltage regulationPower cappingMachine learningRegressionGradient boostingNeural networks

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

AMD

Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1969

Glassdoor: 3.9

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

AMD