GPU Systems Engineer for AI Inference

Nebius Group; Austin (TX); Teletrabalho; USD 150 000 - 230 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative culture

Impactful AI projects

International environment

Resumo da oferta

Nebius is building a standalone AI cloud platform with a focus on scalable GPU-based inference. The role targets engineers who can develop low-level kernels and runtime components, improve inference performance, and profile across CPUs and GPUs to optimize end-to-end execution.

You will work with ML and backend teams to integrate support for new hardware architectures and contribute to a fast, reliable inference stack used at scale.

Qualificações

• Strong C++ proficiency with focus on high-performance coding and memory management.
• Experience in GPU programming or systems-level software development.
• Hands-on profiling and debugging to identify performance issues on CPUs/GPUs.

Responsabilidades

• Develop and optimize low-level kernels and runtime components for AI inference.
• Improve performance of inference engines on GPU platforms.
• Profile and debug system- and hardware-level performance issues.
• Integrate support for new hardware architectures (Hopper, Blackwell, Rubin).
• Collaborate with ML and backend teams to optimize end-to-end execution.

Conhecimentos

C++ proficiency

GPU programming

Profiling & debugging

Memory hierarchy

Ferramentas

perf

VTune

Nsight

ROCm profiler

Descrição da oferta de emprego

Nebius is building a standalone AI cloud platform with a focus on scalable GPU-based inference. The role targets engineers who can develop low-level kernels and runtime components, improve inference performance, and profile across CPUs and GPUs to optimize end-to-end execution.

You will work with ML and backend teams to integrate support for new hardware architectures and contribute to a fast, reliable inference stack used at scale.