Job Description Play a critical role in the development and application of data science algorithms and advanced analytics techniques across a variety of use cases, including recommendation models, email personalization, and segmentation.Build models over various datasets, to analyze importance/centrality (Page Rank,) , similarity (KNN, TF-IDF, etc.
)Design and analyze experiments across user experience on the application, as well as over email communications (A/B, multivariate)Perform analyses of user data and provide feature teams with an understanding of how users are interacting with their productBe able to take tasks that are at times, ambiguous and not so clearly defined, and find the specific requirements by communicating with the appropriate team leadsAssemble large, complex data sets that meet functional / non-functional business requirements.Identify, design, and implement internal process improvements: automating manual processes, optimizing data delivery, re-designing infrastructure for greater scalability, etc.Be able to clearly and concisely communicate to senior leadership the complexities of the models that have been built and how they will be used/impact end users.Approach issues and new feature development with creative solutionsBe able to write code and properly manage versions and deployment across environmentsQualificationsMust have skills:Strong experience working with data science/ML libraries in Python (SciPy, NumPy, TensorFlow, SciKit-Learn, etc.
)Strong experience working in cloud development environments (especially Azure, ADF, PySpark, Scala, DataBricks Delta, R, SQL)Experience building data science models for use on front end, user facing applications, such as recommendation modelsExperience with REST APIs, JSON, streaming datasetsExperience working with user behavioral data,such as web analytics (Google/Adobe Analytics)Experience building ML models and pipelines using MLflow, AirFlow.Experience with big data tools: Hadoop, Spark, Kafka, etc.Experience with relational SQL and NoSQL databases.Experience with stream-processing systems: Storm, Spark-Streaming, etc.Understanding of Graph data, neo4j is a plusStrong understanding of RDBMS data structure, Azure Tables, Blob, and other data sourcesExperience with test driven developmentExperience in PowerBI or other toolsUnderstanding of Jenkins, CI/CD processes using Git, for cloud configs and standard code repositories such as ADF configs and Databricks