Senior ML Engineer (Token Factory)
Nebius
Netherlands
8 May 2026
Netherlands
8 May 2026
Senior ML Engineer (Token Factory)
Nebius is seeking a Senior ML Engineer to join their Token Factory team, building a high-performance inference and fine-tuning platform for LLMs. The role requires deep expertise in machine learning, GPU profiling, and software engineering, with experience in Python and modern deep learning frameworks.
Hybrid
Full-time
Senior
Python
Machine Learning
Salary
Not specified
Core Qualifications
Technical (Must-have)
PythonMachine LearningTransformersGPU profilingNsightPyTorch profilerMHARoPEKV-cacheFlash AttentionquantisationCI/CDversion controlunit testing
Soft Skills
communicationleadership
Preferred Qualifications
Technical (Nice-to-have)
vLLMSGLangTensorRT-LLMTritonCuteCUTLASSCUDA
Key Responsibilities
- Identifying LLM inference bottlenecks to drive production speedups.
- Implementing novel speculative decoding architectures.
- Optimising components of various LLM designs (dense/MoE, autoregressive/parallel).
- Contributing to open-source inference engines.
- Designing and productionising low-precision (FP8, NVFP4/MXFP4) training and inference pipelines.
Senior ML EngineerToken FactoryNebiusInference OptimizationLLMGPUPythonDeep LearningHybridAmsterdam