I am a lead software engineer in the data team at Yieldbot. Yieldbot is an advertising network, and my responsibility is the matching technology: how to find ads that are relevant to the user based on the contents of page, how to choose between the ads and bid on adslots to maximize profits and meet other business constraints, and how to do all this at scale with low latency and high availability.
I was previously a computational biologist at the Broad Institute of MIT and Harvard, working with Anne Carpenter and her Imaging Platform. My work there turned measurements of billions of invidividual cancer cells into computational profiles ("fingerprints") that capture the biologically meaningful aspects of the cells’ appearance. Such profiles can be used to find similar genetic perturbations and/or drugs. I developed analysis methods that apply machine learning and data mining methods to large sets of complex, dirty, and poorly understood data.
My research interests are in distributed systems, databases, index structures, algoriths, and data science (see my publications), but I am an engineer at heart, motivated by building real systems that can manage the complexity and be robust to the curve balls thrown by large, real-world workloads. I thrive when I build and scale cool technology that makes a difference together with a competent and respectful team.
I often get asked how to spell and pronounce my name. My name is spelled "Vebjørn Ljoså" in Norwegian, but I use "Vebjorn Ljosa" outside Norway. I pronounce my name [ˈʋêːˌbjǿɳ ˈljûːsˌóː]. Speakers of English can often come close with "vay-b-yearn lyo-soa". (But if it doesn’t come out quite right, it doesn’t bother me!)
Last updated: 2018-10-29