Data Science Manager - Application Fraud

Manage and mentor a team of data scientists building fraud detection models and financial risk products. Own end-to-end model development from data acquisition through production, while driving technical direction and cross-functional planning.

About the job

Responsibilities

Directly manage a team of highly skilled data scientists. Start from 2-3 and grow to 5-6.
Act as a technical mentor that can dive deep and provide detailed direction.
Lead planning, resourcing and communications with senior leadership, product and engineering teams.
Develop strong business intuition and guide your team to deliver performant DS solutions on aggressive timelines.
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.
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.

Requirements

10+ years relevant work experience & relevant Masters or 7+ years & relevant PhD.
2-5 years experience directly managing a team of data scientists, ideally in a startup environment.
3+ years of startup experience.
Excellent communicator and team player.
Proven track record of solving complex / high profile business problems with DS / ML solutions.
Experience in communicating outcomes / progress to senior management / stakeholders.
Very strong in “end to end” DS development: Planning, fleshing out success criteria / metrics, getting buy-in, developing the solution, delivering the solution (prod / deck / strategy doc / etc).
Strong practical ML / Stats knowledge, i.e. can easily employ the suite of standard ML / stats tools to quickly scope out solutions, and double down where needed. Experience with SOTA ML solutions is a plus.
Interest in developing deep domain expertise for product-focused work: a background in fraud is not required, but willingness to learn is.
Experience writing production code and tests.
Detail oriented and thoughtful—someone we can rely on to make business-changing decisions.
Thrive in a fast paced environment characterized by the need to solve extremely varied, high impact, open ended problems.