Senior SoC Power Modeling Engineer

Advanced Micro Devices, IncAustin, TX
11d

About The Position

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. We are seeking a Senior Power Modeling Engineer to drive pre-silicon power modeling and analysis for AMD’s next-generation Embedded x86 SoC platforms. This role plays a critical part in defining use-case-driven power expectations, building SoC-level power models from IP inputs, and enabling informed EDC/TDC, voltage-frequency (VF), and PPA trade-off decisions early in the design cycle. THE PERSON: The ideal candidate brings deep hands-on experience with SoC power modeling methodologies and understands how IP-level power characteristics scale to full-chip behavior. This engineer will collaborate closely with SoC architects, power architects, performance teams, and silicon validation teams to ensure accurate power projections and influence architectural direction. This role is not eligible for visa sponsorship.

Requirements

  • Professional experience in power modeling, power estimation, or SoC power analysis
  • Strong understanding of: SoC power architecture and DVFS Static vs dynamic power components EDC / TDC / electrical and thermal constraints
  • Hands‑on experience building SoC‑level power models from IP‑level models
  • Experience creating and analyzing VF curves
  • Strong analytical and scripting skills (Python preferred)
  • Ability to work across architecture, IP, performance, and validation teams
  • Ability to clearly communicate modeling assumptions and results to senior technical stakeholders
  • BS/MS in Electrical Engineering, Computer Engineering, or related field

Nice To Haves

  • Experience with Embedded or Automotive SoCs
  • Familiarity with x86 CPU, GPU, memory, and fabric power behaviors
  • Exposure to power modeling tools, spreadsheets, or internal frameworks used for pre‑silicon estimation
  • Experience with workload‑driven modeling and benchmark abstraction
  • Prior involvement in power correlation with silicon

Responsibilities

  • Develop and maintain SoC-level power models for Embedded x86 platforms using IP-level inputs (CPU, GPU, fabric, memory, and I/O).
  • Create use-case-driven power models representing automotive, industrial, edge computing, and customer-specific embedded workloads.
  • Translate real-world workloads into model inputs such as activity factors, concurrency, residency, and DVFS states.
  • Build and maintain Voltage‑Frequency (VF) curves across operating corners.
  • Derive and validate EDC / TDC / current limits based on modeled workloads and platform constraints.
  • Perform sensitivity studies across frequency, voltage, workload mix, and power states.
  • Integrate IP‑level power models into cohesive SoC‑level frameworks.
  • Ensure consistency of assumptions across IPs (clocking, power states, gating, DVFS).
  • Identify gaps, inconsistencies, or inaccuracies in IP models and drive closure with IP teams.
  • Partner with SoC and power architects to influence early architectural decisions.
  • Evaluate power/performance/area trade‑offs for new features, configurations, and SKUs.
  • Support bounding‑box analysis and product positioning decisions.
  • Support pre‑silicon to post‑silicon correlation of power models.
  • Refine models using silicon data, profiling, and validation feedback.
  • Improve modeling methodologies, accuracy targets, and documentation.

Benefits

  • AMD benefits at a glance.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service