Microsoft Research Intern - Finetuning Post Training Quantization 

United States, Washington 

971532322

Finetuning optimizations for driving extreme datatypes and quantization for LLM inference. This project would explore research ideas pushing towards lower bits (~2 bits/param and below) with novel encoding and tuning methods.

• Currently enrolled in a PhD program in Computer Science or a related STEM field.
• At least 1 year of experience with systems optimizations for deep learning training and finetuning.

Other Requirements

• Research Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
• In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position as well as a cover letter and any relevant work or research samples. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter.

• Hands-on expertise with deep learning tools and frameworks, such as Pytorch, DeepSpeed, and FSDP.
• Demonstrated ability to develop and prototype original research agendas.
• Ability to collaborate effectively with other researchers and product development teams.
• Proficient interpersonal skills, cross-group, and cross-culture collaboration.

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: