GPU ML Benchmarking Engineer for Next-Gen AI Infra

Nebius; Amsterdam (VA); On-site; USD 130,000 - 190,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative and innovative culture

Impactful AI projects

Job summary

Nebius is building a full-stack AI cloud platform and seeks a highly skilled ML/AI Engineer to lead benchmarking of GPU platforms for ML workloads. You will evaluate GPU performance across platforms and frameworks and help drive platform optimisation and future hardware development.

You will profile at system and kernel levels, debug ML workloads, and develop dashboards to visualise performance trends. Collaboration with hardware, software, and cloud teams is essential.

Qualifications

• Benchmark GPU platforms for ML workloads and AI frameworks.
• Profile and analyse GPU performance at system/kernel level.
• Debug and optimise ML workloads on GPU hardware.

Responsibilities

• Profile GPU performance across platforms and architectures.
• Evaluate CUDA/ROCm performance for AI workloads.
• Develop tools/dashboards to visualize performance trends.
• Perform acceptance testing for GPU clusters for AI workloads.
• Collaborate with hardware and software teams for optimisation.
• Contribute to internal tooling and best practices.

Skills

GPU benchmarking

Performance profiling

PyTorch

JAX

Megatron-LM

Tensor-LLM

Tools

Nsight

nvprof

Docker

Kubernetes

Job description

Nebius is building a full-stack AI cloud platform and seeks a highly skilled ML/AI Engineer to lead benchmarking of GPU platforms for ML workloads. You will evaluate GPU performance across platforms and frameworks and help drive platform optimisation and future hardware development.

You will profile at system and kernel levels, debug ML workloads, and develop dashboards to visualise performance trends. Collaboration with hardware, software, and cloud teams is essential.