Hybrid Data Scientist II — ML & Fraud Analytics

Early Warning Services, LLC; New York (NY); Hybrid; USD 122,000 - 162,000; Full time

Benefits offered by this job

Healthcare coverage

401(k) retirement plan

Paid time off

Parental leave

Maven Family Planning

Job summary

Early Warning Services LLC is seeking a data scientist to contribute to end-to-end ML and AI initiatives. You will work across terabytes of data, delivering production-ready code and collaborating with product and engineering teams to uncover insights and drive business impact.

The role emphasizes translating complex analyses for non-technical audiences while upholding data integrity and privacy. A hybrid work model is in place with US-based eligibility to work.

Qualifications

• Bachelor’s degree in Mathematics, Statistics, Computer Science, Operational Research or related field.
• Minimum of 4 years data science, engineering, mathematics, or related work experience.

Responsibilities

• Explore and aggregate data to uncover anomalies affecting algorithm performance.
• End-to-end feature engineering—from brainstorming to down-select.
• Write production-level code in a dynamic environment.
• Solve problems on terabyte-size data sets.
• Apply ML techniques to business problems to identify optimal approaches.
• Partner with Product and Engineering teams to find trends and opportunities.
• Explain and visualize results and algorithm performance to non-technical audiences.
• Support data systems’ integrity and confidentiality.

Skills

Python

SQL

Machine learning

Big data

Data visualization

Production code

Communication

POC prototyping

Education

Bachelor's degree

Tools

scikit-learn

MLlib

Job description

Early Warning Services LLC is seeking a data scientist to contribute to end-to-end ML and AI initiatives. You will work across terabytes of data, delivering production-ready code and collaborating with product and engineering teams to uncover insights and drive business impact.

The role emphasizes translating complex analyses for non-technical audiences while upholding data integrity and privacy. A hybrid work model is in place with US-based eligibility to work.