AI Engineer

## AI Engineer Apply:
Hybrid:
Chicago (Green St), IL:
Full time:
Posted Yesterday:
0014925

Salary range is:

This position is bonus and/or commission eligible.

CCC Intelligent Solutions Inc. (CCC) is a leading cloud platform for the multi-trillion-dollar insurance economy**,
** creating intelligent experiences for insurers, repairers, automakers, part suppliers, and more. At CCC, we’re making life just work by empowering more than 35,000 businesses with industry-leading technology to get drivers back on the road and to health quickly and seamlessly. We’re pushing boundaries with innovative AI solutions that simplify and enhance the claims and repair journey. Through purposeful innovation and the strength of its connections, CCC technologies empower the people and industry relied upon to keep lives moving forward when it matters most.

Learn more about CCC at  
** The Role
** You will build and ship LLM-powered features and agentic workflows for our customers. These features automate the routine parts of a claim and guide customers on the rest, so they have to earn that trust with measured accuracy, not a convincing demo. Agents run as steps inside deterministic workflows, and privacy and security are design baselines, not review gates. Agentic coding tools are how you move fast.

What you add is what they are worst at: system design, security, and hard debugging. You own features end to end.#
*
* Key Responsibilities:

*** Ship LLM-powered features and agentic workflows in Python and Type Script, from a problem scoped with product managers and data scientists through production traffic, and help set the metrics you will be measured against.
* Write the evals, guardrails, and feedback loops that make your features trustworthy, and hold them to explicit token and latency budgets.
* Use agentic coding tools every day, and own the review of what they produce: catch the correctness, security, and design problems in generated code before you open the pull request.
* Maintain and extend the NLP pipelines that turn unstructured claim data into structured data customers can act on, blending semantic search, classical NLP, and LLMs.
* Build and operate durable, event-driven services in which agents run as steps inside deterministic workflows, with check pointed model outputs so a retry does not re-invoke a completed LLM step.
* Trace every model call and agent step so a recommendation can be reconstructed and audited, with citations back to the source documents, and wire that tracing into your alerts.
* Model and query claims data across relational, document, and graph stores.
* Design privacy and security in from the start: tenant isolation, least-privilege access for agents and their tools, and a clear rule for what personal and medical data may reach a model provider.
* Write a technical design document before any significant change, and use it to get feedback and buy-in from the team before you build.
* Take part in a shared on-call rotation for the services you build.#
** Requirements:
*** 3+ years of professional software engineering experience, including at least one LLM-powered feature you shipped and then operated in production.
* Python and Type Script: typed, tested, async code in both, and real depth in one.
* Evals you have designed for LLM output, plus guardrails you have shipped.
* A clear account of how you constrain an agentic coding tool's context and verify its output, from daily use of Claude Code, Cursor, Git Hub Copilot, or similar on production work.
* Pipelines that blend LLMs with semantic search and classical NLP: structured output, tool calling, embedding-based retrieval, and a case where a classical technique beat an LLM.
* Services built on message- or event-driven architectures, including…