System Engineer - AI Inference Kernel & GPU Runtime

Devconnectplatform; Amsterdam; A distancia; EUR 70.000 - 110.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Competitive compensation

Career growth and learning

Flexible work arrangements

Descripción de la vacante

Nebius is hiring a System Engineer for the Token Factory within Nebius Cloud. The role focuses on building and optimizing low-level kernels and runtime components for AI inference, with emphasis on GPU platforms and end-to-end performance.

You will collaborate with ML and backend teams to push the limits of throughput and efficiency across CPU/GPU architectures, including new hardware support. This is a remote-friendly, international role with a strong emphasis on ownership and impact.

Formación

• Strong proficiency in C++ or GPU programming with low-level high-performance coding.
• Experience in GPU programming or systems-level software development (OS internals, kernel modules, drivers).
• Hands-on profiling and debugging to optimize CPU/GPU performance.
• Knowledge of CPU/GPU architectures and memory hierarchies.

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-level and hardware-level performance issues.
• Integrate support for new hardware architectures (Hopper, Blackwell, Rubin).

Conocimientos

C++ programming

GPU programming

Linux

Herramientas

Perf

VTune

Nsight

Descripción del empleo

Nebius is hiring a System Engineer for the Token Factory within Nebius Cloud. The role focuses on building and optimizing low-level kernels and runtime components for AI inference, with emphasis on GPU platforms and end-to-end performance.

You will collaborate with ML and backend teams to push the limits of throughput and efficiency across CPU/GPU architectures, including new hardware support. This is a remote-friendly, international role with a strong emphasis on ownership and impact.