Experience
- 4+ Years
Education
- BE/ BTECH/MCA/MSC Computers preferred
Location
- Work from office (Koregaon Park, Pune)
Required Skills
- Proficiency in Python is necessary.
- Ample exposure to data wrangling and analysis of structured text data using `pandas` and related libraries.
- Exposure to `pyspark`.
- Familiarity with data transformation and modeling techniques such as Clustering, NLP, and Entity Resolution.
- Knowledge of statistical learning methods.
Responsibilities
- Data Exploration – discovery of industry data sources to support building out industry-specific knowledge graph.
- Data Wrangling – data quality assessment and transformation using NLP techniques, geo-coding.
- Exploratory Data Analysis – conducting exploratory analysis to extract insights and find outvimportant groups, trends, and relationships in data and in the knowledge graph.
- Documentation – report progress and communicate questions via JIRA / confluence.
- Analyzing and Reporting – evaluating discovery results and summarizing conclusions to stakeholders.
Data scientists will get exposure to a wide range of datasets including shipping, supplier, news, and incident data. They will collaborate with the team to build models and pipelines to solve industry problems that will be deployed in a production software environment. They will become familiar with graph database technology and how to query the graph to find relationships of interest to customers.