Eric Kim, MS eric-kim.net
About Me
Hello, my name is Eric Kim!
I am a back-end machine learning engineer on the Advanced Technologies Group at Pinterest. I wear many hats in this role, and have worked on: object detection, DNN serving infrastructure, graph neural network infrastructure, C++ build systems, big-data pipelines (mainly Spark).
In 2016, I completed my MS in computer science at UCLA, where I focused in computer vision and machine learning. In 2011, I graduated from UC Berkeley with a degree in computer science.
My interests are: computer vision, machine learning, teaching, and the intersection of computer science and music.
I developed a novel face verification system within a multilinear framework for my MS thesis. (Link to PDF coming soon)
Here is a recent copy of my CV and resume (Updated February 2022).
Projects
- Software
- FourVoices: An automatic music generator for four-part harmonies (Python).
- Automatic Digit Classification: An automatic digit classifier that applies adaptive spline models to recognize handwritten characters (Matlab).
- L1-norm Approximation: A custom primal-dual interior point solver for the L1-norm approximation problem (Matlab).
- My Github profile
- My LinkedIn profile
- Writing
- Blog Posts: A collection of technical and non-technical articles that I've written.
- Music: My collection of music that I've written and recorded.
- Teaching: Learn more about my teaching experience.
News
- August 2020
- Moved to Orange, CA!
- January 2017
- Accepted a software engineer position at Pinterest!
- June 2016
- Completed my MS at UCLA!
- Aug. 13th, 2013
- I went to EVT/WOTE 2013 at Washington DC, and gave a talk about the OpenCount system, titled: "Improved Support for Machine-Assisted Ballot-Level Audits".
- Feb. 28th, 2013
- OpenCount Poster created and presented at NIST Future of Voting Systems Symposium! Poster PDF
- Jan. 9th, 2013
- Released a new blog post: "Everything You Wanted to Know About the Kernel Trick (But Were Too Afraid to Ask)".
Publications
- "Toward Transformer-Based Object Detection"
- Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk. arXiv 2020.
- "Bootstrapping Complete The Look at Pinterest"
- Eileen Li, Eric Kim, Andrew Zhai, Josh Beal, Kunlong Gu. KDD 2020.
- "Shop The Look: Building a Large Scale Visual Shopping System at Pinterest"
- Raymond Shiau, Hao-Yu Wu, Eric Kim, Yue Li Du, Anqi Guo, Zhiyuan Zhang, Eileen Li, Kunlong Gu, Charles Rosenberg, Andrew Zhai. KDD 2020.
- "Complete the Look: Scene-based Complementary Product Recommendation"
- Wang-Cheng Kang, Eric Kim, Jure Leskovec, Charles Rosenberg, Julian McAuley. CVPR 2019.
- "Three-dimensional soft tissue analysis of the face following micro-implant-supported maxillary skeletal expansion"
- Sara Abedini, Islam Elkenawy, Eric Kim, Won Moon. Progress in orthodontics vol. 19,1 46. 19 Nov. 2018, doi:10.1186/s40510-018-0243-z
- "Improved Support for Machine-Assisted Ballot-Level Audits"
- Eric Kim, Nicholas Carlini, Andrew Chang, George Yiu, Kai Wang, David Wagner. EVT/WOTE 2013.
- "Operator-Assisted Tabulation of Optical Scan Ballots"
- Kai Wang, Eric Kim, Nicholas Carlini, Ivan Motyashov, Daniel Nguyen, David Wagner. EVT/WOTE 2012.
- "An Analysis of Write-in Marks on Optical Scan Ballots"
- Theron Ji, Eric Kim, Raji Srikantan, Alan Tsai, Arel Cordero, David Wagner. EVT/WOTE 2011.
Press
- July 2012, "Saving throw: securing democracy with stats, spreadsheets, and 10-sided dice." (Link)
- A neat Ars-Technica news article highlighting the research work that our group and Professor Philip Stark is doing with the OpenCount project.
Contact
- E-mail
- eric (DOT) kim (DOT) cs (AT) gmail (DOT) com