Lead Data Science Engineer

Arlo•New York City, NY

1d•Onsite

About The Position

Arlo powers healthcare innovation through modern underwriting technology. Small and medium-sized businesses have long seen little innovation in their health plan options and are hit with ever-increasing healthcare costs. As a technology-forward MGU (managing general underwriter), we use modern data science techniques to help health plan architects design novel health plans and leverage value-based care. Our mission is to bring affordable, value-based health benefits to employees of small and medium-sized businesses nationwide. Arlo’s founding team has extensive experience in claims analytics, data science, benefits administration systems, and health plan underwriting. Arlo’s team members previously worked at Palantir, Willis Towers Watson, McKinsey, and a Y-Combinator startup. Arlo has raised a $4M seed round from Upfront Ventures, 8VC, and General Catalyst. At Arlo, we value diverse opinions and debate. We are team-focused learners and seek to understand the missing perspective. Our team is collaborative, ambitious, and passionate about advancing the future of healthcare. We are looking for a motivated team member to join us locally in NYC. Team Overview & Role Impact As a Data Science Engineer, you will own the next iterations of the Arlo underwriting API from modeling to deployment. You will partner closely with our head actuary to refine our model and ideate novel underwriting strategies.

Requirements

2+ years working as a data scientist or engineer
Experience setting up and managing large data pipelines
Experience working with standard machine learning techniques
Experience setting up production-ready API services for model evaluations
An interest in using the best tool for the job. Our current favorites are Python, Sklearn, SQL, PySpark, SparkML, Snowpark, Python API frameworks, AWS, Docker

Nice To Haves

Familiarity with health insurance industry and financial terminology
Experience working with medical and prescription drug claims data
Experience working with probabilistic modeling techniques
Experience working with social determinants of health data sources

Responsibilities

Define and manage the architecture of the Arlo data and machine learning deployment pipelines
Setup a system to manage and maintain the Arlo underwriting models
Design and implement reporting tools from quote data and in-force business
Support the next development iterations of the Arlo underwriting approach
Deploy the Arlo underwriting models into our production environment
Evaluate new data sources for health underwriting and use SDOH features to predict health outcomes