About the Position:
Data scientists at Ledger are critical to the success of the company. Their primary role is to develop impartial estimates of risk/return profiles for insurance-linked securities, which can include the following challenges:
- Blending portfolio-specific and industry-wide data to optimize the bias-variance tradeoff.
- Empirically estimating underwriting team skill based on historical performance.
- Building stochastic estimates of asset cash flows based on loss ratio forecasts and loss development patterns.
- Dynamically updating asset valuations in real-time based on current policy and claims data.
- Forecasting the ultimate disposition of insurance claims that are still open.
- Accounting for material shifts in the composition of a portfolio over time.
If these problems sound fun and interesting, we'd love to have you on our team. We offer competitive compensation, including company stock options. Our headquarters are in Washington, DC, but this position can be full-time remote.
Successful candidates will have all of the following attributes:
- Extensive knowledge of statistics, machine learning, and data science; MS or PhD in statistics or a related field preferred.
- Familiarity with hierarchical modeling, time-series/state-space methods, and/or distribution fitting.
- Demonstrated track record of applying and adapting statistical methods to solve complex real-world problems.
- Extensive experience with R, Python, Julia or other open-source languages with strong numerical computing ecosystems. Ability to produce analyses that are reproducible and easy to understand/modify.
- Ability to integrate data sources from a wide variety of sources (CSV, XLSX, databases, flat files, JSON, etc) and perform checks for integrity, consistency, and accuracy against known sources of truth.
- Ability to work independently and communicate ideas effectively.
The following attributes will help candidates stand out from the crowd:
- Working knowledge of property & casualty insurance, particularly from an actuarial and/or underwriting perspective.
- Familiarity with Bayesian modeling via Stan.
- Familiarity with version control, especially Git/GitHub.