Senior Machine Learning Engineer (Casualty / Claims Intelligence)

CCC Intelligent Solutions•Chicago, IL

About The Position

CCC Intelligent Solutions Inc. is hiring a Senior Machine Learning Engineer for a new, rapidly growing engineering group building AI-native products for its auto casualty business, focused on the injury side of auto claims. The group develops AI products for processing medical bills, supporting claims decisions, and providing the rules engine, agentic tooling, and evaluation infrastructure used across casualty products. The engineer will own models and evaluations end to end within a problem area and use evidence to inform product decisions. The role combines statistical modeling, machine learning, and large language model approaches, along with production engineering. It involves building models on real claims data, evaluating them against expert decisions, and measuring customer impact. Success in the first month means running an evaluation on real data and sharing the findings. Within six months, the engineer is expected to have shipped a model or evaluation to production and informed a product decision with evidence.

Requirements

Typically 5 or more years of experience in machine learning, data science, or quantitative engineering roles.
Strong quantitative foundation in statistics, probability, and experiment design, gained through a degree, research, or equivalent experience.
Strong Python and SQL skills.
Track record of taking models to production and measuring their performance.
Hands-on experience with both statistical machine learning and LLM-based approaches, including RAG, embeddings, and vector search.
Experience evaluating LLM outputs.
Real experience working faster with AI-assisted tools, with examples to discuss.

Nice To Haves

Causal inference, survival analysis, or calibration methods applied to business decisions.
Experience fine-tuning models for domain-specific tasks.

Responsibilities

Build and ship statistical, machine learning, and hybrid LLM models, including retrieval and embeddings, using real claims data.
Design evaluations and gold datasets with data labelers and subject matter experts, and run evaluations continuously as the product changes.
Measure impact through experiment design, baselines, and ROI analysis.
Clearly explain evaluation and impact results to product teams, sales, and customers.
Own models and evaluations end to end within a problem area and use results to inform product decisions.