Power & Performance Engineer - AI Hardware

About the role

Intel is looking for a Power & Performance Engineer in Haifa to help build the next generation of AI hardware solutions. You will join an agile team developing cutting-edge hardware for AI workloads, in a startup-like environment that gives engineers significant technical and business impact. The role uses a modeling and telemetry platform developed by a partner team.

Key responsibilities

• Own pod-level power and performance metrics for large-scale AI data centers, collecting, validating and reporting performance-per-watt, capacity and utilization metrics.
• Operate and drive requirements for the partner's modeling/telemetry platform, and give feedback to improve its accuracy and coverage.
• Aggregate silicon and rack data up to the pod level, reconcile measured versus modeled metrics and own the pod power and performance budget.
• Drive power telemetry, capping and dynamic power management (RAPL, P/C-states, DVFS) to maximize throughput within pod thermal and power envelopes.
• Build workload characterization and benchmarking pipelines (SPEC, MLPerf, AI workloads) to identify bottlenecks and guide pod capacity planning.
• Partner with facilities, electrical and the platform team on power distribution, PUE targets and peak-demand management at pod scale.

Required profile

• Bachelor's, Master's or PhD in Electrical Engineering, Computer Engineering, Computer Science or a related technical field.
• 5+ years of experience in power, performance, systems optimization or related areas.
• Preferred: experience with PUE/thermal modeling, pod-level capacity planning and AI cluster scaling.

Required skills

• Deep knowledge of CPU/GPU power management, performance counters and Linux power frameworks.
• Data analysis with Python and/or SQL.

The position is an experienced hire in Israel (Haifa, with Petah-Tikva listed as an additional location) and is eligible for a hybrid work model.