Model Validation Data Scientist

About the Team/Role

Designs, develops and programs methods, processes, and systems to consolidate and analyze unstructured, diverse "big data" sources to generate actionable insights and solutions for client services and product enhancement. Interacts with product and service teams to identify questions and issues for data analysis and experiments. Develops and codes software programs, algorithms and automated processes to cleanse, integrate and evaluate large datasets from multiple disparate sources. Identifies meaningful insights from large data and metadata sources; interprets and communicates insights and findings from analysis and experiments to product, service, and business managers.

Apply data science domain knowledge to perform technical independent validation of machine learning and statistical models

Develop and enrich risk domain expertise by engaging with experts in Credit Risk, Fraud Risk, Financial Forecasting, and Operations to understand model design requirements

Assess code and implementation design for model development and deployment

Design creative testing and automated scripts to assess model robustness on large volumes of data and a variety of conditions

Keep abreast with emerging best practices in risk modeling, machine learning, product development, and strategy to apply and improve processes

Synthesize findings into actionable insights and articulate them both in narrative documentation and verbal presentations to senior leadership

Proactively identify and communicate challenges, opportunities, and risks associated with models and projects

Master's or Ph.D. degree in a quantitative field such as Data Science, Mathematics, Computer Science, Statistics, or other technical field

2+ years of professional or research experience as a data scientist, model developer, model validator, statistician, or applied scientist.

Understanding of inner-workings of statistical and machine learning algorithms and their strengths and weaknesses.

Excellent analytical problem-solving and critical thinking skills with attention to detail.

Proficiency with SQL to extract and transform large datasets.

Proficiency of scripting languages such as Python or R and experience with common data science libraries such as scikit-learn, lightgbm, pandas, numpy etc.

Strong written and oral communication skills with an ability to relate complex analytics findings to business outcomes

Solutions oriented and proactive to solve problems collaboratively both in a team of technical and non-technical colleagues and independently in a self-starting manner.

Prior model validation or model development experience in risk models or in a fintech or financial services company

Understanding of model risk regulatory requirements (SR 11-7, OCC 2011-12) and typical governance framework of lines of defense

Experiences leveraging cloud platforms to develop and serve models, such as AWS

Prior experience with Sagemaker, Dataiku, Snowpark/Snowflake, Git, or other similar platform tools

Practitioner experience in an end-to-end ML lifecycle, such as git version control, data acquisition, CI/CD integration, parallel model runs, and model serving