Senior HPC & AI Benchmarking Engineer

Lenovo; United Kingdom; Remote; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Employee Assistance Program

Training & Development Platform

Job summary

Lenovo is seeking an experienced HPC/AI benchmarking specialist to validate and optimise large-scale HPC and AI platforms across compute, storage, networking, and GPUs. You will work with customers, architects, and engineering teams to ensure performance targets and successful deployments.

The role requires deep knowledge of MPI, CUDA, GPU architectures (H100/H200), and Linux administration, with a focus on delivering practical optimisation recommendations and robust benchmark reports.

Qualifications

• Experience with HPC environments including cluster architectures and Linux
• Ability to design and execute HPC benchmarks and validate performance
• Strong knowledge of MPI, OpenMP, CUDA, and GPU-accelerated apps
• Experience with storage and networking in HPC and AI workloads
• Familiarity with industry benchmarks (HPL, HPCG, IO500, MLPerf) and profiling tools
• Excellent communication for customer-facing benchmark reports and docs
• Automation scripting in Python for benchmarking workflows

Responsibilities

• Validate, benchmark, and optimize large-scale HPC/AI platforms
• Design and execute benchmarking plans across compute, storage, networking, GPUs
• Profile apps to identify bottlenecks and propose optimisations
• Work with customers and engineering teams to ensure successful deployment
• Contribute to benchmarking methodologies and knowledge sharing

Skills

HPC environments

Linux administration

MPI

CUDA

NVIDIA GPU tech

Benchmarking

Python automation

Communication

Project leadership

Problem solving

Education

Bachelor's degree in CS/EE or related field

Tools

HPC benchmarks (HPL, HPCG)

Lustre/GPFS

NVIDIA CUDA toolkit

Job description

Lenovo is seeking an experienced HPC/AI benchmarking specialist to validate and optimise large-scale HPC and AI platforms across compute, storage, networking, and GPUs. You will work with customers, architects, and engineering teams to ensure performance targets and successful deployments.

The role requires deep knowledge of MPI, CUDA, GPU architectures (H100/H200), and Linux administration, with a focus on delivering practical optimisation recommendations and robust benchmark reports.