LegalZoom.com is seeking an experienced Python/SQL backend developer to assist in the development of our predictive modeling capabilities. Develop, refactor, test, and deploy scientific projects using Python. Work to help establish best practices in our software development lifecycle, setup project structures, integrate version control using Github, along with environment setups using Anaconda. Develop projects using Amazon AWS, GPU’s, and HPC’s. Participate in refactoring backend SQL scripts, consolidating SQL scripts into stored procedures, and contributing to our data development and test strategies. Also help develop a robust test framework, incorporating both unit and regression tests for better release management.
What you’ll do:
- Work to improve performance and efficiency of our data science codebase using Python and SQL
- Help develop data science prototypes, and translate them to production capabilities with robust validation
- Develop a robust test framework (unit and regression tests) for multiple models used across the organization
- Refactor current predictive models and extract commonly used functions into a reusable set of packages and libraries
- Set up and establish version control in LegalZoom’s enterprise Github repository
- Manage environments using Anaconda
- Help to develop a release management process, and work with the Data Services team to deploy new models to our production environment.
- Support and extend existing predictive models for customer LTV, marketing forecast, subscription retention, micro-segmentation, etc.
- Extract and develop data using SQL with SQL Server
- Help drive and refine requirements for mockups, and prototyping
- At least a B.A., in either Computer Sciences, Mathematics, Statistics, or a similar discipline.
- At least 3 year experience in Python
- At least 3 years SQL development experience to extract and manage data from SQL Server
- Exceptional communication skills and an ability to effectively discuss and present technical information to analytics, engineers, and business users.
- The ideal candidate should also have experience with various scientific packages in Python, including numpy, pandas, scikit, matplotlib, etc.
- Experience with Excel and/or Tableau
- Experience with the software development lifecycle
- Experience managing projects with GitHub and Anaconda
- Ability to manage multiple, competing priorities
- Experience with probabilistic programming using PyMC or PyMC3, a plus
- Knowledge of deep learning frameworks, Keras, Theano, Tensorflow a plus