Advertisement
Job Description:
Samsung is hiring a DNN Model Optimization Expert Engineer for its Neural Acceleration team in Bangalore, India. The role focuses on developing and optimizing accelerated runtime technologies for on-device GenAI, LLM, LVM, machine learning, and deep learning models. The team works on advanced on-device ML inference and training platforms, combining machine learning, deep learning, system software, and SoC capabilities to achieve high-performance system KPIs. The engineer will contribute to DNN model optimization, neural acceleration, runtime platforms, and scalable ML technologies for next-generation devices. This is an on-site opportunity at Samsung's Phoenix Building, Bangalore, and is suitable for professionals interested in AI/ML, Deep Learning, Neural Networks, GenAI, LLM optimization, ML inference, and system-level acceleration.
About Company:
Samsung is a global technology company with a broad presence across consumer electronics, mobile technologies, semiconductors, displays, software, artificial intelligence, and advanced computing technologies. Samsung invests heavily in AI, machine learning, semiconductor technology, SoC platforms, and intelligent device technologies. The Neural Acceleration team in Bangalore focuses on building advanced on-device ML inference and training platforms, particularly for emerging GenAI, LLM, LVM, and neural network workloads. The team combines machine learning, deep learning, system software, and SoC capabilities to develop high-performance AI acceleration technologies. This role provides an opportunity to work on DNN optimization, AI runtime platforms, neural acceleration, on-device AI, GenAI model execution, and scalable machine learning technologies.
