Avner May

Avner May 

Staff Research Scientist at together.ai
CV

About me

I am a staff research scientist at together.ai, working on algorithms for efficient LLM inference. Prior to joining Together, I was a research scientist in Google's speech recognition group (2020-2023), and a postdoctoral scholar working in Prof. Chris Ré's group at Stanford University (2018-2020). I completed my PhD in Computer Science at Columbia University in December 2017, advised by Prof. Michael Collins. Prior to my PhD, I worked for two years as a software development engineer at Microsoft, living in Seattle, WA. I graduated in 2009 from Harvard College, where I majored in Mathematics, with a minor in Computer Science. I am originally from Potomac, MD.

Research Interests

My research interests center around designing simpler, better understood, and more efficient, machine learning models.

Most recently, I have been focusing on designing novel speculative decoding algorithms to speed up LLM inference. During my postdoc, I studied how to design high quality compressed feature representations in various contexts (e.g., word embeddings, kernel approximation features). In my PhD, I showed that kernel approximation methods can perform comparably to fully-connected deep neural networks on the challenging non-linear classification problems in speech recognition systems.

Other Interests

I love most things that involve being active and outdoors — running, biking, snowboarding, hiking, camping, and basically anything in the mountains. During the summer of 2017 I spent 2.5 months on the Pacific Crest Trail. I am very interested in food systems and nutrition, and how they affect our health, the environment, and the well-being of animals.

Publications

* Equal contribution.

Internships

Community Service