AI Engineer

CCC Intelligent Solutions Inc. is hiring an AI Engineer to help build and deploy LLM-powered capabilities that automate claim tasks with measured accuracy, privacy, and security in mind. You will own features end to end, spanning evaluation and guardrails, durable event-driven services, tracing and auditing, and NLP pipelines that convert unstructured claim data into structured outputs.

This role is based in Chicago, IL (onsite), and you will collaborate with product managers and data scientists from early scoping through production traffic, including defining the metrics used to judge impact.

What you’ll do

• Ship LLM-powered features and agentic workflows using Python and TypeScript, partnering with product managers and data scientists from problem definition through production traffic, and helping set the metrics you will be measured against.
• Develop evals, guardrails, and feedback loops that make model-driven features trustworthy, with explicit token and latency budgets.
• Use agentic coding tools daily and own review of generated code, focusing on correctness, security, and design before code is opened in a pull request.
• Maintain and extend NLP pipelines that transform unstructured claim data into structured data customers can act on, combining semantic search, classical NLP, and LLMs.
• Build and operate durable, event-driven services where agents run as steps in deterministic workflows, using checkpointed model outputs so retries do not re-invoke completed LLM steps.
• Trace every model call and agent step to support reconstruction and auditing, including citations back to source documents, and wire tracing into alerts.
• Model and query claims data across relational, document, and graph stores.
• Design privacy and security from the start, including tenant isolation, least-privilege access for agents and tools, and clear rules governing what personal and medical data may reach a model provider.
• Write a technical design document for significant changes and use it to gather feedback and obtain team buy-in before building.
• Participate in a shared on-call rotation for the services you build.

What you bring

• 3+ years of professional software engineering experience, including at least one LLM-powered feature you shipped and operated in production.
• Strong Python and TypeScript experience, with typed, tested, async code in both and real depth in at least one.
• Hands-on experience designing evolutions for LLM outputs (e.g., evals) and shipping guardrails.
• A clear account of how you constrain agentic coding tool context and verify outputs, including experience with tools such as Claude Code, Cursor, GitHub Copilot, or similar in production work.
• Experience building pipelines that blend LLMs with semantic search and classical NLP, including structured output, tool calling, embedding-based retrieval, and at least one example where classical methods outperformed an LLM.
• Experience with message- or event-driven architectures, long-running workflows with retries, idempotent handlers, and event-sourced state, including running an LLM or agent step inside one.
• Backend data modeling experience across PostgreSQL, MongoDB, Neo4j, SQL Server, and Cosmos DB, with depth in at least one relational and one non-relational store, plus familiarity with tenant isolation and regulated personal data.
• Experience building and operating backend services on Azure or AWS, and familiarity with durable workflow engines such as Temporal or Durable Task Scheduler.
• Experience writing technical design documents to obtain feedback and buy-in, and evidence that the team built to those plans.
• Clear technical writing and discussion skills for both technical and non-technical audiences, along with strong code review collaboration.

Technologies you may work with

• Python, TypeScript
• Claude Code, Cursor, GitHub Copilot
• Semantic search, classical NLP, LLMs
• Embedding-based retrieval, structured output, tool calling
• Message- or event-driven architectures, long-running workflows, idempotent handlers, event-sourced state
• PostgreSQL, MongoDB, Neo4j, SQL Server, Cosmos DB
• Tenant isolation, Azure, AWS
• Temporal, Durable Task Scheduler
• React, Terraform, Bicep
• LangGraph, Microsoft Agent Framework
• Model Context Protocol (MCP), Agent2Agent (A2A) protocol
• Microservices, LangSmith, Arize, Braintrust
• OpenTelemetry, CI/CD, A/B tests

Compensation and benefits

• Salary: USD 119,030 - 150,000 per yearly
• 401K Match
• Paid time off
• Annual Incentive Plan Performance Bonus
• Comprehensive health insurance
• Adoption Assistance
• Tuition Reimbursement
• Wellness Programs
• Stock Purchase Plan options
• Employee Resource Groups

Even better if you have

• React and TypeScript experience to deliver full-stack features end to end, including 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 including LangGraph and the Microsoft Agent Framework, and knowledge of how agents reach tools via MCP, A2A, command-line tools, and microservices.
• Experience with LLM observability and evaluation tooling 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 before release.
• Exposure to insurance, claims, or automotive repair domains.

Interview policy and privacy notice

• A video interview is required for this position.
• Video interviews are transcribed.
• Transcriptions are retained and may be reviewed by CCC and their recruiters.
• Candidates are not permitted to use generative AI or automated assistance during the interviews unless explicitly allowed by the interview team for a specific exercise.
• The Job Applicant Privacy Notice is available HERE.

Success looks like: within six months you ship an LLM-powered feature with evals running in CI and can name the metric it moved; evals catch regressions caused by model migrations or prompt changes before customers do; you take ownership from concept to production with light direction; your services handle retries, partial failures, and model migrations without customer-visible incidents; production traces let you pinpoint the step and model call and support auditing; privacy and security reviews find no issues outside the intended design; your patterns spread through the team; you contribute to scoping and technical discussion with clarity; and you value measured outcomes, collaboration, and empathy.