System Engineer (Token Factory)
Remote • Remote; Remote - Europe
Posted 5d ago
Remote Work Policy
Fully remote
Categories
AI Engineer
About the job
Nebius is building a full-stack AI cloud platform to support developers and enterprises in the global AI economy. We are focused on solving complex problems across compute, storage, networking, and applied AI. The Token Factory team is developing a cutting-edge inference platform designed to make various foundation models (text, vision, audio, and multimodal) fast, reliable, and effortlessly deployable at massive scale.
Responsibilities
- Develop and optimize low-level kernels and runtime components for AI inference.
- Improve the 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.
Requirements
- Strong understanding of system-level programming and performance optimization.
- Experience with GPU programming and optimization techniques.
- Proficiency in C++ and CUDA.
- Familiarity with AI inference frameworks and libraries.
- Experience with profiling and debugging tools.
- Ability to work with new hardware architectures.
- Experience collaborating with ML and backend teams.