Samsung GPU ML Architect 

United States, California, San Jose 

589564232

Role and Responsibilities

We are seeking a highly skilled GPU ML Architect to join our GPU Architecture hardware team. As a GPU ML Architect, you will be responsible for designing and developing innovative machine learning (ML) solutions for graphics processing units (GPUs). While knowledge of graphics or GPU architecture is not a requirement, a strong understanding of compute architectures and machine learning principles is essential. You will work closely with cross-functional teams to analyze workloads, model performance, and create new features for large vision models and image classification applications.

• You write technical specifications for new ML features and architectures, ensuring they integrate seamlessly with the graphics pipeline and meet performance, power, and functionality requirements.
• You work on improving middleware to enhance the overall performance and efficiency of ML workloads on GPUs.
• You create new hardware features and optimizations to improve PPA on ML applications such as LLMs, LVMs, Image Classification, etc.
• You integrate with the graphics pipeline team to ensure that ML solutions are aligned with the overall graphics architecture.
• You optimize GPU architectures for ML workloads, ensuring maximum performance and power efficiency.
• Collaborate with engineers to analyze and model workloads, identifying performance bottlenecks and areas for optimization.

Skills and Qualifications

• 15+ years of experience with a Bachelor’s degree in Computer Science/Computer Engineering/relevant technical field, or 13+ years of experience with a Master’s degree, or 11+ years of experience with a PhD
• Strong understanding of machine learning principles and architectures
• Experience with compute architectures and performance optimization
• Experience with workload analysis and modeling
• Excellent programming skills in languages such as C++, Python, or similar
• Familiarity with LLMs, LVMs, and image classification
• GPU architecture and graphics pipeline experience is a big plus
• Knowledge of ML frameworks and tools (e.g., TensorFlow, PyTorch) preferred
• Ability to write clear and concise technical specifications
• Strong analytical and problem-solving skills

U.S. Export Control

This position requires the ability to access information subject to U.S. export control restrictions. Applicants must have the ability to access export-controlled information or be eligible to receive a government authorization to access export-controlled information.