Senior Data Scientist
GrubHub is the nation's leading online and mobile food-ordering company dedicated to connecting hungry diners with local takeout restaurants. The GrubHub portfolio of brands includes GrubHub, Seamless, MenuPages and Allmenus. The company's online and mobile ordering platforms allow diners to order directly from thousands of takeout restaurants across the country and London, and every order is supported by the company's 24/7 customer service. GrubHub has offices in Chicago, New York City and London.
With a career at GrubHub you can order your cake and eat it, too!
We are looking for a highly technical Senior Data Scientist to join our exciting and growing Operations team. The Operations team is charged with coordinating data-driven decision making across GrubHub’s business operations with a particular focus on modeling, optimizing, and reporting on our delivery logistics. This is a new team within GrubHub, and we are still making initial investments in developing our core models and reporting infrastructure in the context of a rapidly evolving business. This position will be heavily involved with complex data science (machine learning) problems, solving business issues, and improving GrubHub’s performance vs. competitors.
Responsibilities:
Proactively acquire knowledge about business processes and identify possible improvements by data/prediction
Acquire necessary data for models from internal stakeholders, external services and data providers
Iterate on predictive models from quick PoC to show value added and, finally, full production roll-out
Collaborate with other Data Scientists with regard to sharing best practices and peer review process
Requirements:
5 - 7 years of experience crunching data for insight (including academic experience)
Any relevant analytical background is welcome (physics, mathematics, finance, bioengineering, retail etc.)
Excellent data-related programming skills (e.g. SQL, R, Python, Mathamatica or choose your tool) with ability to provide code samples
Superior data presentation and visualization skills (e.g. D3, Tableau, Arcadia, Angular etc.) with ability to provide examples (anonymized please)
Experience building automated analytical pipelines into production (from ETL job on data sources to visual/notification output for end users)
Strong verbal and written communication skills
Knowledge and understanding of mathematics underlying key machine learning algorithms ( e.g. logistic regression, neural networks, random forest, gradient boosted trees)
Proficient in preparing data for machine learning (missing values, outliers, skewed data, PCA, feature manufacturing etc.)
Experience balancing external data sources (features) vs. tinkering with machine learning model selection for best/quickest results
Ready to apply existing & best-in-class machine learning techniques to business problems vs. “ permanent scientific discovery mode”
Quick, eager learner & teacher, sharing is your passion
Ability to complete each code iteration according to “reproducible science” principles
Preferred Requirements:
Experience working for an online retailer
Any Big Data experience & Spark
Experience participating in Kaggle.com competitions
Experience building real-time or near-real-time (e.g. 1 min delay) analytics
Experience applying distributed Machine Learning
NLP pipeline experience (e.g. NTLK, WordNet, Word2Vec, Open NLP etc.)
GrubHub Inc. is an EQUAL EMPLOYMENT OPPORTUNITY/AFFIRMATIVE ACTION employer.