Senior AI Engineer

CCC Intelligent Solutions•Chicago, IL

About The Position

CCC Intelligent Solutions Inc. is hiring a Senior AI Engineer to own LLM-powered systems and agentic workflows for customers. The systems automate routine claim tasks and guide customers through other parts of the claims process. The role owns a product area end to end, from scoping ambiguous customer problems with product managers and data scientists through production operation, and defines the evaluation standards the product must meet before release. The engineer designs NLP pipelines and durable, event-driven, multi-tenant systems where agents run as steps inside deterministic workflows. They establish evaluation, reliability, privacy, and security practices; maintain tracing and auditability for model calls and agent steps; and use agentic coding tools while ensuring generated code meets the team's quality standards. The role also involves technical design and code review, mentoring, and participation in a shared on-call rotation. CCC describes itself as a cloud platform serving the insurance economy and more than 35,000 businesses. Its technology supports insurers, repairers, automakers, and parts suppliers, with AI solutions intended to improve the claims and repair journey. The company describes its culture as ambitious, collaborative, and empathetic, and highlights values of Integrity, Customer-Focus, Innovation, Inclusion & Diversity, Tenacity, and Connection.

Requirements

At least 6 years of professional software engineering experience.
Experience architecting and shipping an LLM-powered system to external customers and carrying it through at least one model or prompt migration.
Strong Python and TypeScript experience, including setting shared-codebase conventions for asynchronous programming, typing strictness, and testing, and profiling and fixing a performance issue.
Experience establishing an evaluation and guardrails strategy for a product area, including deciding when human approval is required and how production corrections feed back into evaluations.
Daily production use of an agentic coding tool such as Claude Code, Cursor, or GitHub Copilot; ability to explain how its context and output are constrained and verified, including examples of rejected changes and the reasons.
Experience designing pipelines that combine LLMs, semantic search, and classical NLP, including defensible retrieval design and an example where a classical technique outperformed an LLM on cost, latency, or reliability.
Experience designing durable, event-driven systems with deterministic orchestration around non-deterministic model steps, including compensating actions, idempotency, backpressure, and event-sourced replay.
Data modeling and development across relational, document, and graph databases such as PostgreSQL, MongoDB, and Neo4j, including decisions about fit, partition keys, consistency, and tenant isolation.
Experience architecting and operating systems on Azure or AWS, with CI/CD and infrastructure as code.
Hands-on experience with a durable workflow engine such as Temporal or Durable Task Scheduler.
Experience authoring technical design documents for systems spanning more than one team, using them to obtain feedback and buy-in before implementation, and having the teams build to those designs.
Clear written and verbal communication with technical and non-technical audiences, including eliciting customer needs and explaining trade-offs.

Nice To Haves

React and TypeScript experience delivering full-stack features, especially chat, streaming, and citation-heavy AI experiences.
Experience with agent frameworks such as LangGraph, PydanticAI, or Microsoft Agent Framework, and agent tool-access approaches such as MCP, A2A, command-line tools, and microservices.
Experience with LLM observability and evaluation tools such as LangSmith, Arize, or Braintrust, and OpenTelemetry-based tracing.
Experience designing A/B tests for AI features.
Exposure to insurance, claims, or automotive repair domains.

Responsibilities

Own delivery of LLM-powered systems in Python and TypeScript, from scoping customer problems with product managers and data scientists through production operation.
Define evaluation and guardrail strategies, including release gates, production signals, and simulations against historical claims before changes ship.
Improve the team's use of agentic coding tools by refining specifications, instruction files, hooks, and permission policies, and reviewing generated code to the team's standards.
Design NLP pipelines that transform unstructured claim data into structured information, selecting among semantic search, classical NLP, and LLMs.
Build and operate durable, event-driven, multi-tenant systems in which agents run within deterministic workflows; plan failure modes, replay semantics, and costs.
Own tracing and audit practices so model calls and agent steps are recorded and recommendations can be reconstructed and traced to their sources.
Establish privacy and security baselines, including tenant isolation, least-privilege access, redaction, retention, and controls on data sent to model providers.
Write design documents for complex systems, obtain feedback and buy-in, review other engineers' designs and code, and mentor engineers in the product area.
Participate in a shared on-call rotation for owned systems.
In the first six months, gate every model change in the area with designed evaluations, catch regressions before customer impact, and demonstrate maintained or improved accuracy.
Turn high-stakes, ambiguous problems into roadmaps, shipped systems, and measurable customer-facing results.
Help establish durable standards for evaluations, reviews, design documents, privacy, and security, and mentor engineers to ship LLM features with evaluations and guardrails.
Collaborate with product managers, data scientists, and customer teams to agree on scope and explain trade-offs.