Senior AI Engineer (CCC Casualty / Claims Intelligence)

EvolutionIQ•Chicago, IL

About The Position

CCC Intelligent Solutions is hiring a Senior AI Engineer for a new, growing engineering group building AI-native products for its auto casualty business, focused on the injury side of auto claims. The team works on AI products for handling medical bills, decision support for claims professionals, and an Agentic Rules Platform that supports decisions across casualty products and provides evaluation infrastructure. The engineer will own AI agents within a problem area from prototype through measured production performance. This includes building agents that work with complex documents and claim data, call tools, and support claims experts. The role owns agent orchestration, retrieval, evaluation, and guardrails, as well as the production code needed to ship those systems. The position is bonus eligible, with a stated salary range of $180,000–$225,000. Expected early outcomes include shipping a measured improvement to an existing agent in the first month and having an agent built by the engineer in production with customers, supported by evaluation results, within six months.

Requirements

Typically 5 or more years of professional software or machine learning engineering experience, including meaningful recent work with LLMs.
Strong production engineering skills in Python, including API services, and comfort working in TypeScript.
At least one year of experience shipping LLM-powered products to real users, including retrieval such as RAG, embeddings, or vector search, and prompt engineering.
Experience designing evaluations for non-deterministic systems and measuring the effects of changes.
A quantitative mindset, including comfort with metrics, sampling, error analysis, and determining whether results are real.
Real experience shipping faster with AI-assisted or agentic engineering tools, with examples to discuss.

Nice To Haves

Experience with document understanding, OCR, or extraction from complex documents.
Experience fine-tuning LLMs or working with multimodal data.

Responsibilities

Design and build LLM-powered agents and workflows, including orchestration, tool use, retrieval, structured extraction, and human-in-the-loop review.
Build evaluations with data labelers and subject matter experts, and run evaluations on every change.
Make agents production-grade through guardrails, observability, cost and latency management, and careful handling of sensitive health data.
Own agents end to end within a problem area, from prototype to measured performance in production.