Applied ML Scientist, New Grad

SentiLink

1d•Remote

About The Position

As an Applied ML Scientist at SentiLink, you will build our core products: models that identify fraudsters and also advance our growing suite of products in financial risk. This role is designed for new PhD graduates or early-career researchers interested in applying machine learning to real-world fraud detection. You'll build and ship machine learning models in a production environment, gaining hands-on experience across the full ML lifecycle, from research and development to deployment at scale. If you're looking for real-world AI and ML exposure in an industry setting, not just research papers, this is it.‹ We have open roles on multiple teams including: Emerging Products - focuses on 0-to-1 development of new offerings brought to market Application Fraud - analyzes the foundational elements of consumer financial applications to detect all forms of fraud Identity - resolves identities across massive, often conflicting data sources (both digital and physical) and generates risk models from limited information You will be relied upon to be technically capable and the definitive owner of your respective domain. You will often work on projects with high visibility and impact that require deep domain understanding, critical thinking and strong technical abilities. You will work with teams across the company to research new types of fraud, develop new products, and provide analysis to drive sales and marketing. This is a full-stack data science role, involving model development, analysis, and writing production code. You should be interested in having end-to-end ownership and a fast-moving environment where deep domain understanding drives development and unusual insights drive our competitive advantage rather than optimization of new machine learning methodologies. This role can be remote within the U.S., with a strong preference for candidates who can work from our Austin, San Francisco, or New York offices.

Requirements

Bachelor’s, Master’s, or PhD in Statistics, Computer Science, Physics, Mathematics, or a related quantitative field or equivalent experience/research
Strong foundation in machine learning, statistics, or applied data science
Experience with Python and common data science tools through coursework, research, internships, or personal projects
Demonstrated ability to analyze complex problems and build data-driven solutions
Strong communication skills and ability to explain technical ideas clearly
Interest in learning deeply about fraud, identity, and financial risk systems
Ability to write clean, maintainable code
Strong attention to detail and curiosity about real-world data problems
Candidates must be legally authorized to work in the United States and must live in the United States
Thrive in a fast paced environment characterized by the need to solve extremely varied, high impact, open ended problems

Responsibilities

Develop and maintain SentiLink’s fraud detection models through the full model development lifespan: from data acquisition decisions through featurization, focusing labeling resources, model training, experimentation, productionalization, and monitoring.
Build foundational modeling to drive SentiLink’s expanding suite of Fraud and Financial Risk products.
Research new types of fraud and develop new SentiLink products around identity verification.
Achieve success by researching / developing through iteration, integration of new data sources and inventive feature engineering.
Write production-ready code that can be relied on for real-time decision making by our partners.
Design, perform, and present analyses that will inform data acquisition, product development, risk operations priorities, marketing, and sales efforts.
Work with engineering, risk operations, and data acquisitions to access necessary data, maintain data quality, and support data access