AI Power & Performance Engineer

About the role

We are seeking an experienced AI Power & Performance Engineer to join our AI System PnP team. The candidate will evaluate, benchmark, profile, and optimize AI inference workloads across modern CPU, GPU, APU, and heterogeneous computing platforms. We are seeking an experienced AI Power & Performance Engineer to join our AI System PnP team.

What you'll do

• Benchmark and characterize AI inference workloads using PyTorch, ONNX Runtime, vLLM, llama.cpp, TensorFlow, and related technologies
• Analyze latency, throughput, memory utilization, power consumption, and performance per watt
• Profile workloads and identify bottlenecks across AI frameworks, runtimes, operating systems, memory subsystems, and hardware
• Optimize workload performance through quantization, graph optimization, kernel tuning, memory optimization, and heterogeneous compute utilization
• Automate benchmark execution, data collection, regression analysis, and results visualization

What you need

• 5–10 years in data science & ai
• Python
• PyTorch
• TensorFlow
• Linux
• Data analysis
• Bash
• B.Tech or B.E.

Good to have

• Machine learning
• LLMs
• Docker