Tech Stack

Description

You will build and improve machine learning and GenAI models for underwriting decisions, taking ownership from data exploration through deployment. You'll collaborate with underwriters, product managers, and engineers to turn complex insurance signals into reliable decisioning systems that help Coalition assess and price cyber risk at scale.

Requirements

• Ph.D. or MS in quantitative/computational field (CS, Statistics, Applied Math, EE) or equivalent
• 5+ years full-time experience developing and deploying ML solutions in production
• Hands-on experience with supervised and unsupervised learning, including model selection, regularization, calibration
• Expertise in statistical analysis: regression, inference, forecasting/time-series
• Proficiency in Python and ML libraries (scikit-learn, XGBoost/LightGBM, PyTorch/TensorFlow) and SQL

Responsibilities

• Build and advance ML and GenAI models for underwriting decisions and risk selection
• Drive ML projects end-to-end: problem framing, data exploration, feature engineering, model design, prototyping, evaluation, deployment, monitoring
• Design and implement ML pipelines for preprocessing, feature engineering, training, tuning, and evaluation
• Apply state-of-the-art ML and GenAI workflows (gradient-boosted trees, deep learning, LLMs, prompt engineering) to improve underwriting accuracy
• Own model quality and robustness by defining success metrics, running ablations, and iterating