Power & Performance Engineer

About the role

Join a fast‑moving, startup‑like team developing next‑generation AI hardware. You will own power and performance metrics for large‑scale AI data‑center pods, driving both technical excellence and business impact.

Key responsibilities

• Own pod‑level power and performance metrics, collecting and reporting performance‑per‑watt, capacity, and utilization data.
• Operate and improve the modeling/telemetry platform, reconciling measured vs. modeled metrics.
• Drive power telemetry, capping, and dynamic power management (RAPL, P/C‑states, DVFS) within thermal and power envelopes.
• Build workload characterization and benchmarking pipelines (SPEC, MLPerf, AI workloads) to identify bottlenecks.
• Partner with facilities, electrical, and platform teams 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 related field.
• 5+ years of experience in power, performance, or systems optimization.
• Deep knowledge of CPU/GPU power management, performance counters and Linux power frameworks.
• Proficiency in data analysis using Python and/or SQL.

Required skills

• Python
• SQL
• Linux power frameworks
• RAPL (Running Average Power Limit)
• DVFS (Dynamic Voltage and Frequency Scaling)
• CPU and GPU power management
• Performance counters
• SPEC and MLPerf benchmarking

What we offer

• Hybrid work model allowing split time between on‑site (Haifa) and remote work.