Principal Research SDE - GPU Optimization - Microsoft Research

Last updated one month ago
Location:Redmond, Washington
Job Type:Full Time

Microsoft Research (MSR) ensures the company’s future by inventing and building the next generation of technologies, tools, and algorithms. One of our most ambitious current projects involves building the world’s most advanced compiler engine for AI workloads. A state-of-the-art optimizing compiler is key to training and deploying state-of-the-art AI models, moving AI workloads from the cloud to the edge, end reducing the carbon footprint of AI workloads in the cloud.

We’re looking for motivated software engineers with a passion for writing high performance code. Specifically, we’re hiring engineers with experience implementing and optimizing algorithms on GPUs. Join a collaborative team with big dreams, working on one of the hottest and most important topics in the company.

This job description is written for a Principle level position, but we are also hiring at other levels.

Responsibilities

Responsibilities:

  • Write high performance reference implementations of DNN operators and linear algebra functions that match or beat common GPU frameworks
  • Design and implement optimization techniques for AI workloads
  • Tune GPU compute kernels for optimal performance
  • Modify algorithms to run more effectively on the GPU
  • Participate in engineering and research activities that ensure the compiler engine generates byte code that outperforms your best hand written code
  • Work closely with experts in Machine Learning, Optimization, Algorithms, and Compilers

Qualifications

Required qualifications:

  • 8+ years professional experience in C++
  • 8+ years of experience shipping products over multiple release cycles
  • 2+ years experience in high performance computing and programming GPUs


Preferred qualifications

  • Outstanding collaboration and communication skills
  • Fluency in C++14 or higher
  • Experience tuning GPU compute kernels for improved performance
  • Experience porting computational algorithms to run efficiently on GPU
  • Experience with assembly level programming and debugging
  • Experience programming in Python
  • MS/PhD degree in Computer Science or related field

Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request via the Accommodation request form.

Benefits/perks listed below may vary depending on the nature of your employment with Microsoft and the country where you work.