Arlo Senior Data Scientist at Arlo owning underwriting model development and continuous improvement based on real-world outcomes. Works with large-scale claims data to identify predictive signals and deploy scalable solutions.
Responsibilities
Underwriting is at the core of Arlo. Every group we price depends on how accurately we can estimate the risk of the individual members inside, and the quality of the estimate is essential to the sustainability of our business. We’re hiring a Senior Data Scientist to own our underwriting model and continuously deploy measurable improvements to it based on learnings from real-world outcomes. You’ll work with billions of claims across tens of millions of patients to identify what signals in claims history predict future medical cost, how to roll it up to a competitive price for a group, and how to deploy the system at scale. You’ll constantly monitor the lifecycle of predictions, group policies sold, and claims incurred by our tens of thousands of members to gather novel insights that can improve our model and pricing approach.
This is a hands-on modeling role in which you will sit on the underwriting team alongside our team of data scientists and actuaries thinking through issues beyond point estimates of cost including how to handle data blindness, variability, and when the risk is too high to issue a quote. You’ll own the model but work alongside ML engineers to ensure that your ideas can be tested and deployed at scale.
Evaluate the existing Arlo underwriting model and find where it breaks
Develop a robust evaluation framework to stress the model outcomes and identify specific gaps in risk estimates (cohorts, conditions, or claims patterns) and the underlying causal factors
Use those findings to generate a roadmap of model and feature work that is prioritized based on making sure our rates are competitive in the market while ensuring we can remain a profitable business.
Build features that capture the full risk of a member
Account for training and inference dataset bias to optimize member predictions
Improve handling of member cost variance in our quoting pipeline
Experiment with model designs
Implement different ML architectures that balance efficacy, generalizability, and understanding so we can outperform the market
Prove the lift before it ships
Work with our backtesting harness to measure the effect of every model change on MLR and competitiveness.
Qualification
Deep proficiency in Python and SQLDirect experience with healthcare dataInterest in the larger business contextBackground in underwriting
Required
5+ years as a data scientist building predictive models that made it into production
Deep proficiency in Python and SQL, with comfort processing large datasets using Spark and using common modeling packages.
A track record of owning a problem end-to-end in an ambiguous environment and shipping without being handed a spec
Direct experience with healthcare data
Strong instincts for feature engineering and model validation, and the judgment of how well results might be able to hold in production
Interest in the larger business context. This is not a research endeavor, but a live model that directly changes our win rates, book size, and performance.
Clear communicator who can explain what they did and why it mattered
Preferred
Familiarity with claims data and their known quirks and biases
Prior experience working at Series C or earlier start-ups
Background in underwriting, actuarial sciences, or risk adjustments
