Performance Engineering Architect
Core
Characterize and optimize the performance of AI solutions across GPUs, servers, storage, networking, and system software to support product design and customer decisions.
Role type
Senior IC Performance Engineering Architect (AI/GenAI)
Builds
HPE Green Lake hybrid cloud platform and AI workloads
Domain
Enterprise server hardware, AI/ML inference, and high-performance computing
Deliverable
production ML models
Required skills
Generative AI performance, GPU benchmarking, LLM serving frameworks, Linux administration, Python scripting, server architecture, performance analysis, automation
Preferred skills
Virtualization platforms, industry benchmarks, database workloads
Technologies
NVIDIA NIM, vLLM, TensorRT-LLM, PyTorch, Kubernetes, Docker, NVIDIA DCGM, fio, SPEC CPU
Responsibilities
Design and execute performance studies for AI workloads, characterize inference and training performance, identify performance bottlenecks, develop custom benchmark suites, automate benchmark execution, produce performance reports, collaborate with engineering and product teams
Seniority
Senior, hands-on IC
