This role is part of the Models and Data Science Team responsible for driving quantitative advanced analytics spanning insights, predictive modeling, and machine learning solutions across business verticals. Specific tasks include building analytical data pipelines by joining disparate data sources, feature engineering, building models using data science methodologies including: regression, supervised / unsupervised learning, causal inference, and Bayesian simulation, measurement of model output on business results, maintaining code and model repositories in GitHub, and building workflow automation following MLOps best practices.   

This role will help business by providing accurate and reliable credit risk models that enable more informed lending decisions, reduce default rates, and improve overall portfolio performance. By ensuring regulatory compliance and enhancing model performance, the role contributes to maintaining financial stability, optimizing capital allocation, and supporting strategic business growth.  

The ideal candidate will be self-driven, highly organized, and an effective contributor in cross-functional data & analytics teams.  They will bring curiosity, effort, and vision to execute projects quickly for their partners. 

Who you are 

• Have a proven record (in academia or industry) of credit risk model development 

• Able to explain your logical and structured thinking/processes in different ways to different people while maintaining the honesty and integrity of your analysis 

• Can provide clear communication and have built charts and visualizations which told an important story 

• Love being part of a fast-moving supportive team and welcome feedback to learn 

• Are organized and able to document what you produce 

• Are comfortable with ambiguity and charting a path through quantitative analysis 

Examples of potential work  
Much of the work will be acting as an internal consultant within the broader analytics center of excellence, grappling with new initiatives as they emerge from departments across the Consumer & Business  bank.  

One day you might be fitting distributions to historical data and modelling outlier events, the next helping colleagues find anomalies in their data indicative of fraud. Through it all, you will draw upon your toolkit of mathematical understanding and coding skills, and an openness to collaborate to create new algorithms. 
  

Role and Responsibilities 

• Create, implement, and validate machine learning models including rigorous documentation of code and results 

• Investigate, define, and iterate with business partners to define business problems and data science use cases 

• Communicate in person, via email, and in virtual meetings with internal and external team members on updates & status 

• Mine and manipulate data from disparate systems and environments 

• Use statistics to analyze data and produce insights on tight timelines 

• Problem solve on varied and concurrent projects, self-organize your work and projects (with input on prioritizing from team leader) 

• Present materials (visual, verbal) to relevant parties about data science concepts and model results 

Technical Skills 

• 3+ years’ experience in a data science or quantitative role working hands on with code to build predictive models and advanced analytics applied to large-scale data-intensive projects 

• Strong knowledge of credit risk concepts, including PD, LGD, EAD, Stress testing and scorecard development 

• Awareness of model bias and how to mitigate it  

• Honed application of the research process – exploration, hypothesis creation, and iteration 

• Deep understanding of statistics or advanced mathematics like Bayesian inference, optimization, linear algebra 

• Ability to explain failures as well as successes as you build understanding in an emerging area 

• Confidence with cloud computing in AWS or GCP 

• Advanced in at least one machine learning programming language and framework (Python, R, ...) 

• Experience using data science methodologies including regression/classification, XgBoost,  time-series modelling, and algorithm/network optimization 

• Master's or research degree in a quantitative discipline 

EEO Statement:  At Santander, we value and respect differences in our workforce.  We actively encourage everyone to apply.   

Santander is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, genetics, disability, age, veteran status or any other characteristic protected by law.

Working Conditions: Frequent Minimal physical effort such as sitting, standing and walking. Occasional moving and lifting equipment and furniture is required to support onsite and offsite meeting setup and teardown. Physically capable of lifting up to fifty pounds, able to bend, kneel, climb ladders.

Employer Rights: Employer Rights: This job description does not list all of the job duties of the job. You may be asked by your supervisors or managers to perform other duties. You may be evaluated in part based upon your performance of the tasks listed in this job description. The employer has the right to revise this job description at any time. This job description is not a contract for employment and either you or the employer may terminate at any time for any reason.

Primary Location: Boston, Ma (Hybrid)

Other Locations Considered: New York City, NY; Miami, FL; Dallas, Tx

Organization: Santander Bank, N.A.

The base pay range for this position is posted below and represents the annualized salary range. For hourly positions (non-exempt), the annual range is based on a 40-hour work week. The exact compensation may vary based on skills, experience, training, licensure and certifications and location.

Base Pay Range

Minimum:

Maximum: