Low-Level GPU Systems Engineer – AI Inference

Nebius Group; Brussel; Sur place; EUR 120 000 - 180 000; Plein temps

Avantages offerts par ce poste

Competitive compensation

Career growth

Flexible work environment

Résumé du poste

Nebius is advancing AI infrastructure with Token Factory, a high-performance GPU cloud platform. The role focuses on building and optimizing low-level inference kernels and runtime components for massive-scale AI workloads.

You will work closely with ML and backend teams to improve end-to-end execution, profile system and hardware performance, and integrate support for new GPU architectures to push efficiency and reliability across Nebius cloud services.

Qualifications

• Strong proficiency in C++ with emphasis on performance and memory management.
• Experience in GPU programming or systems-level software development (OS internals, kernel modules, device drivers).
• Hands-on profiling and debugging of CPU/GPU workloads to optimize end-to-end execution.

Responsabilités

• 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 (e.g., Hopper, Blackwell, Rubin).
• Collaborate with ML and backend teams to optimize end-to-end execution.

Connaissances

C++ high-perf

GPU programming

Systems development

Profiling & debugging

Description du poste

Nebius is advancing AI infrastructure with Token Factory, a high-performance GPU cloud platform. The role focuses on building and optimizing low-level inference kernels and runtime components for massive-scale AI workloads.

You will work closely with ML and backend teams to improve end-to-end execution, profile system and hardware performance, and integrate support for new GPU architectures to push efficiency and reliability across Nebius cloud services.