Senior Data Scientist (Machine Learning - Ranking) (OpenTable, Inc., San Francisco, CA)
Build effective search ranking models with non-parametric non-linear Gradient Boosted Tree Algorithms (including XGBoost, LightBGM, and CatBoost) and Neural Networks. Generate Natural Language Processing (NLP) snippets for restaurants and neighborhoods for Search Engine Optimization (SEO). Build sophisticated supervised and unsupervised Machine Learning and statistical models for data analysis, classification and regression. Build restaurant neighborhood classifiers to enhance restaurant ranking metrics. Extract raw restaurant and diner booking data on Amazon Web Services (AWS), clear data, and upload the transformed data files using Scala and Python. Proactively perform data exploration to understand trends and patterns in restaurant data and identify anomalies. Extract insights from data points to improve the user experience. Integrate data ingestion, extraction, and transformation into formats for modeling and analysis. Interpret A/B experiments to improve specializing dining and search reservation models. Design, analyze and interpret experiment results. Use excellent oral and written communication skills to collaborate with engineers to decide which data to cache for autocomplete ranking projects.
1 Montgomery St., Suite 700
San Francisco, CA 94104
MINIMUM REQUIREMENTS: Master’s degree or U.S. equivalent in Artificial Intelligence, Machine Learning, Computer Science, Applied Statistics, Applied Mathematics, Statistics, Neuro-linguistic Programming, Engineering, Stochastic Signal Processing, Mathematical Statistics and Probability Theory, Applicable Mathematics, Engineering, or a related field, plus 1 year of professional experience in designing, developing, testing, deploying, maintaining and improving large-scale Machine Learning systems. Must also have the following: 1 year of professional experience in building Machine Learning and statistical models (including Boosting or Ensemble methods, and Regression, Linear Models, Support Vector Machines, Hidden Markov Models, Graphical Models, Mixture Models, Markov Decision Processes, Clustering Techniques, Time Series, Deep Learning/Neural Networks, and Bayesian Optimization) to make predictions from a large volume of data; 1 year of professional experience in designing, implementing, and debugging high-volume production-level search ranking systems; 1 year of professional experience in implementing and integrating data ingestion, ETL (extract, transform, load), analysis, and data-mining systems; 1 year of professional experience in implementing monitoring and introspection tools in Machine Learning systems; 1 year of professional experience in maintaining high availability for mission-critical systems; 1 year of professional experience developing approaches and methods for solving data-driven problems; 1 year of professional experience in developing software using Java, Scala, Python, and SQL; 1 year of professional experience with Data Science and Mathematics programming language (including R programming language or MATLAB (Matrix Laboratory); 1 year of professional experience in designing A/B test frameworks and A/B test experiments; 1 year of professional experience in implementing data introspection and monitoring/alerting tools in the context of Machine Learning Technology; 1 year of professional experience in building robust, real-time software systems in distributed environments; 1 year of professional experience in presenting complex scientific topics.
CONTACT: Please submit resume online at: https://boards.greenhouse.io/opentable/jobs/4380491002
Please specify ad code KCLG. EOE. MFDV.
Incentives offered through the company’s Employee Referral Program are applicable to this position. For more information please visit our intranet