Power & Performance Engineer
Core
Own pod-level power and performance metrics for large-scale AI data centers, optimizing throughput within thermal/power envelopes and driving capacity planning.
Role type
Senior IC power and performance engineer (AI hardware)
Builds
AI data center silicon and rack infrastructure
Domain
Semiconductor / AI Hardware / Data Center Infrastructure
Deliverable
production ML models | product features | infrastructure
Required skills
CPU/GPU power management, performance counters, Linux power frameworks, data analysis (Python/SQL), modeling and telemetry platform operation, workload characterization, benchmarking pipelines
Preferred skills
PUE/thermal modeling, pod-level capacity planning, AI cluster scaling
Responsibilities
Collect, validate, and report performance-per-watt, capacity, and utilization metrics across pods; Operate and drive requirements for the modeling/telemetry platform; Aggregate silicon/rack data and reconcile measured vs. modeled metrics; Drive power telemetry, capping, and dynamic power management (RAPL, P/C-states, DVFS); Build workload characterization and benchmarking pipelines; Partner with facilities and platform teams on power distribution and peak-demand management
Seniority
Senior, hands-on IC
