Data Scientist [PySpark & Machine Learning]
5 - 7 years experience • Financial Services
The Python/Spark Developer will be a member of the teams that designs and develops robust automated solutions in partnership with Model Design teams and other stake-holder groups in Risk and Finance. The ideal candidate will possess strong technical skills and an understanding of data systems, and will execute the end-to-end implementation effort.
- Develop, test, and maintain data and analytics needed for risk and finance models
- Process analysis and process improvement,
- Create and maintain technical documentation,
- Contribute to the group’s knowledge base by finding new and valuable ways to approach problems and projects.
- Deliver high-quality results under tight deadlines
- Experience manipulating and summarizing large quantities of data.
- Knowledge of the consumerlending lifecycle, including loan origination, sale/servicing, default management/loss mitigation
- Degree in computer science or a numerate subject (e.g. engineering, sciences, or mathematics) or Bachelor's degree with 6 years of experience, or Master’s degree with 4 years of experience, or a Ph.D. and two years of experience.
- 2 to 4 yearsexperience designing and developing in Python or Scala.
- 2 to 4 yearsexperience in Hadoop Platform (Hive, HDFS and Spark)
- 3 to 5 yearsexperience with Unix shell scripting
- 3 to 5 yearsexperience with SQL
- 1 to 2 yearsexperience with Machine Learning (preferably Spark-ML)
- Knowledge of Java and Scala
- 5 years' experience with version control tools and processes (Subversion, CVS, Clear Case etc.
- 3 years' experience in programming additional languages, especially C++, R, SAS
- Knowledge of Neural Networks and/or Tensorflow