AI Engineer

CCC Intelligent Solutions•Chicago, IL

About The Position

CCC Intelligent Solutions Inc. is hiring an AI Engineer to build and ship LLM-powered features and agentic workflows for customers. The work automates routine parts of insurance claims and guides customers through more complex steps, with trust grounded in measured accuracy. Agents run as steps within deterministic workflows, and privacy and security are built into the design. The engineer uses agentic coding tools while taking responsibility for system design, security, debugging, and features from concept through production. The role works with product managers and data scientists to scope features, establish metrics, build evaluations and guardrails, and operate production services. It includes extending NLP pipelines that turn unstructured claims data into usable structured information; building durable event-driven workflows with checkpointed model outputs; tracing model calls and agent steps for auditability; working with relational, document, and graph data stores; and designing tenant isolation, least-privilege access, and controls over data sent to model providers. The engineer writes technical design documents for significant changes and participates in a shared on-call rotation. The position’s stated success measures include shipping an LLM-powered feature with evaluations running in CI within the first six months, identifying the metric it improves, and ensuring evaluations catch regressions before customers do. The engineer is expected to take ownership with light direction and build services that tolerate retries, partial failures, and model migrations.

Requirements

At least 3 years of professional software engineering experience, including shipping and operating at least one LLM-powered feature in production.
Proficiency in Python and TypeScript, including typed, tested, asynchronous code in both and substantial depth in at least one.
Experience designing evaluations for LLM output and shipping guardrails.
Daily production use of Claude Code, Cursor, GitHub Copilot, or a similar agentic coding tool, with a clear approach to constraining context and verifying generated output.
Experience building pipelines that combine LLMs, semantic search, and classical NLP, including structured output, tool calling, embedding-based retrieval, and an example where a classical technique outperformed an LLM.
Experience with message- or event-driven architectures, including long-running workflows, retries, idempotent handlers, event-sourced state, and running an LLM or agent step within a workflow.
Experience modeling and developing across relational, document, and graph databases such as PostgreSQL, MongoDB, and Neo4j, including decisions about use cases, partition keys, consistency, and tenant isolation.
Experience building and operating backend services on Azure or AWS, and exposure to a durable workflow engine such as Temporal or the Durable Task Scheduler.
Experience writing technical design documents to obtain team feedback and buy-in before implementation, with the team subsequently building to those designs.
Clear written and verbal communication with technical and non-technical audiences, and ability to give and receive code reviews.

Nice To Haves

React and TypeScript experience to deliver full-stack features, especially chat, streaming, and citation-heavy AI experiences.
Experience with CI/CD pipelines and infrastructure as code such as Terraform or Bicep.
Experience with agent frameworks such as LangGraph and the Microsoft Agent Framework, and agent tool-access approaches including 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 or what-if simulations that replay historical claims through a proposed change before release.
Exposure to insurance, claims, or automotive repair domains.

Responsibilities

Ship LLM-powered features and agentic workflows in Python and TypeScript, from product and data-science scoping through production, and help define success metrics.
Create evaluations, guardrails, and feedback loops for trustworthy features, and manage explicit token and latency budgets.
Use agentic coding tools and review generated code for correctness, security, and design issues before submitting pull requests.
Maintain and extend NLP pipelines that turn unstructured claims data into structured data using semantic search, classical NLP, and LLMs.
Build and operate durable, event-driven services with agents as steps in deterministic workflows and checkpointed model outputs to avoid repeating completed LLM steps during retries.
Trace model calls and agent steps so recommendations can be reconstructed and audited with source-document citations, and connect tracing to alerts.
Model and query claims data across relational, document, and graph stores.
Design privacy and security into systems, including tenant isolation, least-privilege access for agents and tools, and rules governing data sent to model providers.
Write technical design documents for significant changes and obtain team feedback and buy-in before implementation.
Participate in a shared on-call rotation for the services built.