I am a developer, researcher, and hacker with extensive experience with large-scale distributed systems and elastic cloud deployments.
I have split my career between research and development, with research roles at Bell Labs and Adobe Research, and with commercial product development/management roles for Netscape, Adobe, Yahoo!, and MobileIron. Most recently, I was Director of Engineering at MobileIron, and Sr. Director of Cloud Services at Yahoo!. I have a MSCS and BSEE from Stanford University.
My current research focus is to investigate and deploy high-throughput distributed systems for data science pipelines and services, for both real-time and batch computational models. Additional areas of research interest include neural networks, GPU acceleration of data applications and data science algorithms, and application security and exploit detection in defensive contexts.
Brandon Amos, David Tompkins(Dec 18, 2014)
This paper shares our experiences building and benchmarking Spindle as an open source Apache Spark-based web analytics platform. Spindle's design has been motivated by real-world queries and data requiring concurrent, low latency query execution. We identify a search space of Spark tuning options and study their impact on Spark's performance. Results from a self-hosted six node cluster with one week of analytics data (13.1GB) indicate tuning options such as proper partitioning can cause a 5x performance improvement.
2014 IEEE 6th International Conference on Cloud Computing Technology and Science (CloudCom)