-
ID
#20013049 -
Job type
Full-time -
Salary
TBD -
Source
Blend360 -
Date
2021-09-21 -
Deadline
2021-11-20
Data Scientist
Maryland, Columbia, 21044 Columbia USAFull-time
Vacancy expired!
Job Description
- Use NLP to generateproduct description options for businessbased off ofproductdescriptions
- Improve Model Algorithm for Desktop Webproductrecommendations based on digital click stream
- Work with client to explore API as an option vs batch
- Work with practice leaders and clients to understand business problems, industry context, data sources, potential risks,and constraints
- Problem-solve with practice leaders to translate the businessprobleminto aworkableData Sciencesolution; proposedifferent approachesand theirprosand cons
- Work with practice leaders to getstakeholderfeedback, get alignment on approaches, deliverables, androadmaps
- Develop a project plan including milestones,dates, owners, andrisks andcontingency plans
- Create and maintainefficientdata pipelines, often within clients’architecture. Typically, data arefrom a wide variety of sources, internal and external, and manipulatedusing SQL, spark,andCloudbig data technologies
- Assemble large, complex data setsfrom client and external sourcesthat meet functional business requirements.
- Perform data cleaning/hygiene, data QC, and integrate data from both client internal and external data sources on Advanced Data Science Platform. Be able tosummarize and describe data and data issues
- Conduct statistical data analysis, including exploratory data analysis, data mining, and document key insights and findingstoward decision making
- Train, validate, and cross-validate predictive models and machine learning algorithms usingstate of the artData Science techniques and tools
- Document predictive models/machine learning results that can be incorporated into client-deliverable documentation
- Assist client todeploymodels and algorithmswithin their own architecture
Qualifications
- Proficiency with multiple analytic tools including ML andPySparkrequired
- MS degree inStatistics, Math,Data Analytics, or a related quantitative field
- 1+ yearsProfessional experience in Advanced Data Science, such as predictive modeling, statistical analysis, machine learning, text mining, geospatial analytics, time series forecasting, optimization
- Experience with one or moreAdvanced Data Science software languages (R, Python,Scala, SAS)
- Proven ability to deploymachine learning models from the research environment (JupyterNotebooks)toproduction viaproceduralor pipelineapproaches
- ExperiencewithSQLandrelational databases, query authoringand tuningas well as working familiarity with a variety of databasesincluding Hadoop/Hive
- Experience with spark and data-frames inPySparkor Scala
- Strongproblem-solving skills; ability to pivot complex data to answer business questions. Proven ability to visualize data for influencing.
- Comfortable with cloud-based platforms (AWS, Azure, Google)
- Experience withSageMaker,Google Analytics, Adobe Analytics a plus
Additional Information
All your information will be kept confidential according to EEO guidelines.
Vacancy expired!
Report job