Data Scientist II – Model Validation and Monitoring

Role :
Data Scientist II – Model Validation and Monitoring

Location:

Scottsdale AZ (Onsite)

• US Citizen & GC Only
• Must be legally authorized to work in US without need for employer sponsorship now or at any time in the future.

This position serves as a data science team member in the Model Validation and Monitoring Team delivering leading edge machine learning models to our clients. This includes providing effective challenges to model development, conducting model monitoring and performance tracking, providing root cause analysis of model performance, exploring, building, validating, and deploying models.

• Lead model monitoring activities, including tracking performance metrics, detecting model and data drift, identifying data quality issues, providing root cause analysis, and recommending remediation strategies.
• Conduct rigorous model validation by providing effective challenges during model development phases, including performance testing, benchmarking, providing a remediation plan, and documenting to ensure models meet business, technical, and regulatory standards.
• Explore and aggregate data independently to uncover data anomalies that impact algorithm performance.
• Write production level code in a dynamic, start-up environment.
• Solve complex problems using terabyte size data sets.
• Apply a variety of machine learning techniques to a business problem to arrive at an optimal approach.
• Partner with Product and Engineering teams to solve problems and identify trends and opportunities.
• Explain and visualize results and algorithm performance to non-technical audiences.

• A minimum of 2 years of data science, engineering, mathematics, or related work experience is required.
• Experience developing data science pipelines & workflows in Python, R, or an equivalent programming language; experience in writing and tuning SQL; experience handling terabyte-size datasets with Spark.
• Experience applying various machine learning techniques and understanding the key parameters that affect model performance.
• Experience using ML libraries, such as scikit-learn or mllib.
• Experience using data visualization tools.
• Able to write production level code that is well‑written and explainable.
• Ability to effectively communicate findings from complex analyses to non-technical audiences.

• Experience using advanced ML algorithms to build, test, and deploy fraud models.
• Hands‑on experience with PySpark.
• Industry experience in building or validating machine learning models.
• Experience exploring data and finding hidden patterns and data anomalies.