Data Scientist

Role: Data Scientist (Stats Modelling)

Location: San Antonio TX

Hiring mode: Full time

Experience Required - 7\+ Years

Must Have Technical/Functional Skills

Programming: Proficiency in Python, R, and SQL.

Mathematics/Statistics: Strong understanding of statistical techniques, probability, and linear algebra.

Machine Learning: Knowledge of algorithms and libraries like Scikit-learn, TensorFlow, or PyTorch.

Core Roles and Responsibilities

Work with the Insurance Data Science teams to develop, refine, test, and deliver model monitoring capabilities. This will include building prototype data assets, calculating metrics, constructing visualizations/dashboard prototypes, and engaging in technical review with AI/ML Engineers \& Data Scientists.

Looking for model ops and model monitoring support. A scientist with strong cs/engineering skills or an engineer with strong science/analytics experience. Here are the specifics we are looking for:

The candidate may also be called upon to perform ad-hoc data/analysis requests, manage scheduled jobs in the Domino platform, collaborate with AI/ML engineers, and other as needed tasks for improving Model Ops in the Insurance Data Science team.

1. Leverage understanding of models and collaborate with Data Scientists to refactor the code into IT maintainable solutions that follows best practices and meets appropriate coding standards.
2. Read model development and ongoing monitoring documentation and engage with data scientists to design the needed monitoring solution for each model.
3. Read and optimize Model development and production SQL queries to develop ground truth data sets for model monitoring activities.
4. Design and develop prototype tables that align to Client's data modeling and DDLC requirements for seamless traditionalization by Client IT.
5. Conduct thorough quality checks to ensure the accuracy and reliability of the data and processes including unit testing, run-to-run testing, etc.
6. Code and implement solutions primarily in Python, ensuring optimal performance and scalability.
7. Run and interpret completed model monitoring dashboards to monitor for breeches in performance and notify the respective data scientists.
8. Work with data scientists to incorporate monitoring results into Quarto based documentation.