Location
Dresden, Saxony, Germany
Posted
May 23, 2026
Job Description
We are currently looking for a Machine Learning Quantization Engineer to join our client in Dresden, Germany.
You will be joining a cutting-edge AI Chip company, working on a highly scalable inference framework.
You will research, develop, and maintain the machine learning inference framework used for AI Chip Architecture and collaborate with other teams of Engineers and Researchers to facilitate the optimization of Neural Networks.
The ideal candidate will have:
Professional experience with ML frameworks (Tensorflow, PyTorch) in Linux environments.
Experience programming in C/C++
Strong knowledge of ML Algorithms and Modelling Techniques, including semi-supervised and weakly supervised learning, transfer learning, quantization, optimization and LLMs.
Knowledge of MLOps, ModelOps and LMOps.
Experience with Neural Network compression methods is also desirable.
You will be joining a cutting-edge AI Chip company, working on a highly scalable inference framework.
You will research, develop, and maintain the machine learning inference framework used for AI Chip Architecture and collaborate with other teams of Engineers and Researchers to facilitate the optimization of Neural Networks.
The ideal candidate will have:
Professional experience with ML frameworks (Tensorflow, PyTorch) in Linux environments.
Experience programming in C/C++
Strong knowledge of ML Algorithms and Modelling Techniques, including semi-supervised and weakly supervised learning, transfer learning, quantization, optimization and LLMs.
Knowledge of MLOps, ModelOps and LMOps.
Experience with Neural Network compression methods is also desirable.