Principal Engineer, Data Mining, Search, and Genetics- SF based
Local Candidates Please
Ancestry.com is the world's largest online resource for family history. We have helped pioneer the market for online family history research, taking a pursuit that was expensive and time-consuming and making it easy, affordable and accessible to anyone with an interest in their family history. The foundation of our service is an extensive collection of billions of historical records that we have digitized, indexed and put online over the past 13 years.
Key company facts:
· Number of digitized genealogical records: 6 billion
· Number of family trees: 20 million
· Monthly page views: 1 billion
· Number of employees: 850
· Annual Revenue: $400M
Responsibilities:
Design and implement large scale data mining and machine learning models in the areas of record linkage, search relevance and ranking, and recommender systems
DNA matching and Identity by Descent (IBD)
Mine tens of terabytes of data using MapReduce and Hadoop
Implement an experimentation infrastructure with associated tools and processes for quick prototyping and evaluation of novel approaches to modeling
Requirements:
Being a smart person with passion for large scale analytics
5+ years of experience with advanced degree in Computer Science, Statistics, or related field is preferred
Very strong grasp of algorithms and data structures
Command of Python and/or Java
Comfortable working in a Linux environment
Pluses:
Experience in machine learning on MapReduce and Hadoop
Experience in search relevance and/or recommender systems
Bioinformatics background
Experience in statistical learning on medium-size data
Experience in R and/or Matlab
Ability to use knowledge of recent techniques and research to invent and propose new approaches and methodologies
Ancestry.com is a profitable, growing company with a positive, high-energy environment. Together, our dedicated teams are harnessing the power of technology and using it to simplify the way people connect with their families and their unique legacies. Our work environment is fast-paced and challenging, but also extremely exciting. You'll work with a team of passionate, engaged individuals. We offer excellent benefits and a competitive compensation package. Please send your information to herbnj@gmail.com
