Cambridge Research Internship on Compiler-like Tools for LLM Efficiency

The Future AI Infrastructure team at Microsoft Research Cambridge (UK) is dedicated to developing technologies for AI data centers of the future. We are seeking a masters/PhD student to join us in Cambridge winter/spring 2025 to work on automatic, compiler-like tools for LLM efficiency, covering topics such as quantization and parallelization. You will joining a welcoming and highly collaborative environment and work on creative and challenging problems during your internship. 

Required/Minimum Qualifications:   

• Be enrolled in Masters/PhD program in Computer Science/Machine Learning or related discipline 

• Substantial experience across static analysis, verification, constraint solving  

• Substantial experience across LMs, inference, parallelization, quantization 

Other Requirements:  

• Interns are expected to be physically located in Cambridge, UK 

Preferred/Additional Qualifications: 

• Strong technical/scientific communication 

• PyTorch, CUDA, tooling 

• Research and develop novel compiler-like tools for LLM efficiency 

• Design, implement and evaluate such tools 

• Write and present your findings in technical documents or presentations