Senior Staff Pre‑Silicon Power Modeling Lead — x86 SoCs

Advanced Micro Devices, Inc•Austin, TX

1d•Hybrid

About The Position

AMD’s embedded and client x86 programs demand first‑time‑right silicon. You will lead SoC‑level pre‑silicon power modeling—owning the methodology, models, and cross‑functional influence that translate into accurate Perf/Watt projections, robust DVFS/AVFS plans, and silicon correlation that de‑risks program power budgets.

Requirements

B.S./M.S. in EE/CE/CS (or related) with 10+ years in SoC pre‑silicon power modeling/estimation and cross‑domain collaboration.
Demonstrated experience building top‑level SoC power models with high correlation to silicon, including IP‑level VBM integration and workload-based projections.
Hands‑on with EDA/tooling: PowerArtist, PrimeTime PX (or equivalents), activity annotation (FSDB/VCD), UPF/CPF power intent, Python for automation.
Deep knowledge of x86 micro‑architecture (CPU pipelines, caches), GPU/NPU basics, memory subsystems, interconnect/fabric behavior, and power delivery/PDN interactions.
Proven ability to define DVFS/AVFS strategies and drive FW telemetry requirements; familiarity with EDC/TDC/CaC semantics and their impact on power.
A validated SoC power model & scorecard that anchors program power budgets and executive reviews.
Workload‑specific DVFS/AVFS tables and telemetry specs for FW/BIOS enablement.
Correlation reports (estimated vs. measured) and recommendations that accelerate first‑time‑right silicon.

Nice To Haves

Segment experience modeling power for automotive (AEC‑Q100/ASIL) use‑cases, networking throughput workloads, storage I/O patterns, industrial/robotics duty cycles.
System performance modeling familiarity (GEM5/Simics/SystemC) to align Perf/Watt predictions and bottleneck analysis with architecture teams.
Experience creating PnP dashboards/regressions (Python/Jenkins/Grafana/InfluxDB) for continuous tracking.

Responsibilities

Own the SoC power model end‑to‑end using AMD’s converged methodology, delivering accurate workload-based power estimates for CPU/GPU/NPU, fabric/interconnect, memory, and I/O.
Define use‑case power envelopes across automotive, networking, storage, industrial, and robotics segments; partner with product/marketing to derive representative workloads and KPIs.
Drive DVFS/AVFS strategy (P‑states, C‑states, voltage/frequency points), telemetry requirements, and FW hand‑offs based on model outputs; provide early tables and guardrails to FW/BIOS.
Establish IP/subsystem power budgets; run sensitivity studies to guide architectural decisions (e.g., cache sizes, fabric frequencies, NPU/GPU configurations).
Build repeatable model‑to‑silicon correlation plans (CaC/static/dynamic splits, EDC/TDC interactions, droop mitigation) and maintain a power scorecard for program reviews.
Lead tool flows & automation (e.g., PowerArtist, PrimeTime PX; Python‑based pipelines) to ingest activity (FSDB/VCD), generate reports, and publish dashboards for stakeholders.
Collaborate across Architecture, RTL/Design, Physical Design, FW/BIOS, and System PnP to ensure converged Perf/Watt outcomes from concept through bring‑up.