Young and research-intensive, Nanyang Technological University, Singapore (NTU Singapore) is ranked among the world's top universities. NTU's College of Computing and Data Science (CCDS) is a leading college that is known for its excellent curriculum, outstanding and impactful research, and world-renowned faculty. Today, we are ranked #2 for AI and Computer Science by US News Best Global Universities; and #5 for Data Science and AI by QS World University Ranking.

A hot bed of cutting-edge technology and groundbreaking research, the College aims to groom the next generation of leaders, thinkers, and innovators to thrive in the digital age. Located in the heart of Asia, NTU's College of Computing and Data Science is an 'exciting place to learn and grow. We welcome you to join our community of faculty, students and alumni who are shaping the future of AI, Data Science and Computing.

CCDS, in collaboration with the Smart Technologies Lab, which conducts cutting-edge research to tackle complex challenges, offers an excellent platform for individuals to contribute to impactful research, deepen their expertise, and collaborate with a diverse team of professionals. The environment fosters creativity and critical thinking, empowering researchers to make meaningful contributions to the advancement of knowledge and the development of innovative solutions.

Key Responsibilities:

• Conduct research and development on LLM inference, including model optimization, quantization, model compression, batching, caching, and accelerated serving techniques.
• Design and implement experimental frameworks, benchmarking pipelines, and prototype systems for evaluating LLM performance across hardware and software platforms.
• Collaborate with project team members to prepare technical reports, documentation, datasets, and research artifacts.
• Support the preparation of research publications, codes, and grant-related deliverables.
• Participate in regular team meetings and contribute to the problem-solving, design, and implementation of new research ideas.

Job Requirements:

• Preferably bachelor's degree in Computer Science, Computer Engineering, Data Science, Artificial Intelligence, or a closely related discipline.
• Strong programming skills in Python and familiarity with AI/ML frameworks.
• Good understanding of LLM architectures, transformer models, and machine learning fundamentals.
• Experience with model serving / inference optimization.
• Ability to conduct experiments rigorously, analyze results, and document processes clearly.
• Strong problem-solving skills, independence, and ability to work collaboratively in a research team.
• Good communication skills and willingness to contribute to publications or demos.

We regret that only shortlisted candidates will be notified.