Senior Research Fellow, LLM Inference Kernel Optimization

National University of Singapore; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

The National University of Singapore invites applications for the position of Senior Research Fellow in the Department of Computer Science, School of Computing (SoC).

SoC is strongly committed to research excellence in all its dimensions: Searching for fundamental results and insights, developing novel computational solutions to a wide range of applications, building large-scale experimental systems and improving the well-being of society.

Qualifications

• PhD in Computer Science or related field.
• Strong background in computer systems.
• Experience with GPU programming.
• Track record of first-author publications.
• Very good English proficiency in both oral and written communication.

Responsibilities

• Develop an efficient kernel optimization engine for large language model inference services.
• Automate profiling, bottleneck diagnosis, kernel generation and optimization.
• Performance benchmarking and integration with production inference frameworks.

Skills

CUDA

Triton

PyTorch

LLM inference frameworks

Education

PhD in Computer Science or related field

Job description

The National University of Singapore invites applications for the position of Senior Research Fellow in the Department of Computer Science, School of Computing (SoC).

SoC is strongly committed to research excellence in all its dimensions: Searching for fundamental results and insights, developing novel computational solutions to a wide range of applications, building large-scale experimental systems and improving the well-being of society.