Senior ML Engineer (Token Factory)

Slashhash; Amsterdam; Hybrid; EUR 120,000 - 150,000; Full time

Job summary

Nebius in Amsterdam is seeking a Senior ML Engineer for its Token Factory team to build and optimize an inference platform for foundation models. You will develop low-level kernels, enhance GPU inference performance, and integrate new hardware architectures, collaborating with ML and backend teams.

Strong C++ or GPU programming and systems-level experience are required to drive end-to-end execution in a fast-paced environment. This role is based in Amsterdam, focusing on cutting-edge AI infra.

Qualifications

• C++ and GPU programming proficiency required.
• Strong memory management and systems-level software experience.
• Knowledge of operating system internals and kernel modules.

Responsibilities

• 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).
• Collaborate with ML and backend teams to optimize end-to-end execution.

Skills

C++

GPU programming

Memory management

Systems-level software development

Operating system internals

Kernel modules

Device drivers

Profiling tools

Debugging tools

CPU architecture

GPU architecture

Memory hierarchy

Job description

Nebius is seeking a Senior ML Engineer for its Token Factory team in Amsterdam, focused on building and optimizing an inference platform for foundation models. The role involves developing low-level kernels, improving GPU inference performance, and integrating new hardware architectures. Requires strong C++ or GPU programming expertise and systems-level experience.

Technical (Must-have)

• C++
• GPU programming
• Memory management
• Systems-level software development
• Operating system internals
• Kernel modules
• Device drivers
• Profiling tools
• Debugging tools
• CPU architecture
• GPU architecture
• Memory hierarchy

Soft Skills

• Collaboration

Technical (Nice-to-have)

• CUDA
• ROCm
• CUTLASS
• Cute
• ThunderKittens
• Triton
• Pallas
• Mosaic GPU

  Key Responsibilities

  • Develop and optimize low-level kernels and runtime components for AI inference
  • Improve performance of inference engines GPU platforms
  • Profile and debug system-level 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

  C++, GPU programming, Memory management, Systems-level software development, Operating system internals, Kernel modules, Device drivers, Profiling tools, Debugging tools, CPU architecture, GPU architecture, Memory hierarchy