Data Scientist II

Early Warning (Zelle); New York (NY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Early Warning (Zelle) is seeking a data science team member to deliver machine learning solutions end-to-end, from problem understanding to deployment. The role involves exploring data, engineering features, and validating models in collaboration with senior technical and business leaders.

The ideal candidate has 4+ years in data science or related roles, proficiency in Python/R/SQL, ML libraries, and data visualization. Hybrid work model.

Qualifications

• Bachelor's degree in Mathematics, Statistics, Computer Science, Operational Research or related field.
• A minimum of 4 years data science, engineering, mathematics, or related work experience.
• Experience developing data science pipelines & workflows in Python, R or equivalent; experience with SQL.
• Experience applying various machine learning techniques and understanding key hyperparameters.
• Experience using ML libraries, such as scikit-learn, MLlib, etc.
• Experience using data visualization tools.
• Able to write production level, explainable code.
• Interest in proofs of concept/rapid prototyping.
• Ability to communicate findings from analyses to non-technical audiences.

Responsibilities

• Explore and aggregate data to uncover anomalies affecting model performance.
• End-to-end feature engineering from ideation to validation.
• Write production-level code in a dynamic environment.
• Handle terabyte-size datasets and complex problems.
• Apply various ML techniques to business problems to find optimal approaches.
• Collaborate with Product and Engineering to identify trends and opportunities.
• Explain and visualize results to non-technical audiences.
• Support data and model confidentiality and security.

Skills

Python

R

SQL

Machine learning

Data pipelines

Data visualization

Communication

Education

Bachelor's Degree in Mathematics, Statistics, Computer Science, Operational Research or related field

PhD / MSc in Mathematics, Statistics, Computer Science, Operational Research or related field

Tools

scikit-learn

MLlib

PySpark

Job description

At Early Warning, we've powered and protected the U.S. financial system for over thirty years with cutting-edge solutions like Zelle®, Paze®, and so much more. As a trusted name in payments, we partner with thousands of institutions to increase access to financial services and protect transactions for hundreds of millions of consumers and small businesses.

Early Warning follows a hybrid work model to allow for a more collaborative working environment.

Candidates responding to this posting must independently possess the eligibility to work in the United States, for any employer, at the date of hire. This position is ineligible for employment Visa sponsorship.

Overall Purpose

This position serves as a data science team member in the company delivering leading edge machine learning and artificial intelligence concepts from start to finish in collaboration with senior technical and business leaders. This includes understanding the business problem/need, exploring and aggregating data, building and validating algorithms, and deploying completed models to deliver business results.

Essential Functions

• Explore and aggregate data independently to uncover data anomalies that impact algorithm performance
• End to end feature engineering - brainstorm, create, validate, down-select, etc.
• Write production level code in a dynamic, start-up environment
• Solve complex problems using terabyte size data sets
• Apply of a variety of machine learning techniques to a business problem to arrive at 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
• Support the company's commitment to protect the integrity and confidentiality of systems and data.
• Support the company's commitment to protect the integrity and confidentiality of systems and data.

Minimum Qualifications

• Bachelor's Degree in Mathematics, Statistics, Computer Science, Operational Research or related field;
• A minimum of 4 years data science, engineering, mathematics, or related work experience is required.
• Experience developing data science pipelines & workflows in Python, R or equivalent programming language. Experience in writing and tuning SQL. Experience handling terabyte size datasets
• Experience applying various machine learning techniques, and understanding the key parameters that affect their performance
• Experience using ML libraries, such as scikit-learn, mllib, etc.
• Experience using data visualization tools
• Able to write production level code, which is well-written and explainable
• Interest to do lots and lots of proof of concepts/rapid prototyping
• Ability to effectively communicate findings from complex analyses to non-technical audiences.

Preferred Qualifications

• Experience in fraud analytics, particularly developing or validating fraud models at a bank or other financial institution.
• Experience developing or validating banking risk models, including models used in Comprehensive Capital Analysis and Review (CCAR) stress testing or Current Expected Credit Losses (CECL) estimation.
• Familiarity with model risk management practices, including development documentation, validation review, performance monitoring, and communicating model assumptions and limitations.
• Experience with transaction or payment data, fraud patterns, and model evaluation for rare events, including tradeoffs between fraud detection and false positives.
• PySpark experience and familiarity with scalable feature engineering and reproducible data science pipelines.
• Knowledge of advanced machine learning algorithms and experience selecting methods appropriate to the business problem and data.
• A track record of managing ambiguity, prioritizing work, and delivering proofs of concept or model development milestones, with timely communication of risks and dependencies.
• Experience automating data science workflows or adopting shared modeling and feature engineering platforms.
• PhD/MSc in Mathematics, Statistics, Computer Science, Operational Research or a related field.

Physical Requirements

Working conditions consist of a normal office environment. Work is primarily sedentary and requires extensive use of a computer and involves sitting for periods of approximately four hours. Work may require occasional standing, walking, kneeling, and reaching. Must be able to lift 10 pounds occasionally and/or negligible amount of force frequently. Requires visual acuity and dexterity to view, prepare, and manipulate documents and office equipment including personal computers. Requires the ability to communicate with internal and/or external customers.

Employee must be able to perform essential functions and physical requirements of position with or without reasonable accommodation.

The above job description is not intended to be an all-inclusive list of duties and standards of the