Location
Saint Charles, MO | United States
Job description
Looking for a Data Engineer who can be responsible for feature engineering, deploying product updates, identifying production issues, implementing integrations that meet our customers’ needs, and development, automation, and maintenance of model performance tracker. The ideal candidate will have a solid background in software development & engineering, robust Python experience, and will work with other Data Scientists and Data Engineers to ensure that software development follows established processes and works as intended. The Data Scientist will also help plan projects and be involved in project management decisions.
Objectives of this role
- Building and implementing new development tools and infrastructure
- Working on ways to automate and improve development and release processes
- Testing and examining code written by others and analyzing results
- Identifying technical problems on ML Models and conduct refactoring and fixes
- Working with software developers, Data engineers, and Data Architects to ensure that development follows established processes and works as intended
Responsibilities
- Develop software to integrate with internal back-end systems
- Perform root cause analysis of production errors and resolve technical issues
- Develop scripts to automate visualization
- Design procedures for system troubleshooting and maintenance
- Planning projects and being involved in project management decisions
- Design and analyze lift experiments to drive product improvements with cross-functional teams
- Conduct research and analysis to improve the statistical/ML model lift using experimental design and causal inference methods
- Write complex SQL queries to clean, aggregate, and/or impute data from multiple tables and/or across jump servers
- Understanding of complex data models (Star Schema, Data Lakes, Data Warehouse)
- Build cross-functional relationships with SQL developers, business analysts, product owners, Customer Success Managers (CSM), and other key stakeholders to identify opportunities to improve products, drive product launches and influence product roadmaps
Required skills and qualifications
- Bachelor of science degree (or equivalent) in computer science, engineering, or relevant field +2 years of equivalent work experience in DevOps with emphasis on Data Science
- Ability to read and follow workflow and dataflow charts
- Proficiency with Git and GitHub workflows
- Robust knowledge of Python OOP and relevant libraries (scikit-learn, Pandas, TensorFlow, etc.)
- Working knowledge of databases and SQL (Job scheduling, store procedures, etc.)
- Problem-solving attitude
- Understanding of data normalization
- Innate curiosity about how ML models work and how to improve them
- Collaborative team spirit
Preferred skills and qualifications
- Solid foundation on Bayesian statistics and conditional probability
- Working experience with Application Programming Interface (API)
- Experience as a DevOps engineer or in a similar software engineering role
- Basic understanding of A/B testing
- Professional experience with Machine Learning models such as logistic regression, decision trees, clustering techniques, NLP, Computer Vision, Geospatial analytics, and/or neural network
Job tags
Salary
