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. These systems automate routine claim work and guide customers through other parts of the claims process, with accuracy that can be measured and defended as models and usage change. Agents operate as steps within deterministic workflows, with privacy and security treated as design baselines. The engineer owns a product area end to end, including the evaluation standards against which it ships, and uses agentic coding tools while providing system architecture, code quality, security, and debugging expertise. The role involves taking ambiguous customer problems from definition with product managers and data scientists through production operation. The engineer designs NLP pipelines, durable event-driven systems, evaluation and guardrail strategies, and privacy and security standards. They document complex system designs, review designs and code, mentor engineers, and participate in a shared on-call rotation. CCC is a cloud platform serving businesses across the insurance economy, including insurers, repairers, automakers, and parts suppliers. Its technologies support the claims and repair journey and help drivers get back on the road and to health.

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 skills, including setting conventions for asynchronous programming, typing strictness, and shared-codebase testing, as well as profiling and fixing a performance problem.
Experience setting an evaluation and guardrail strategy for a product area, including defining 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 is constrained and output verified, including examples of generated changes rejected and why.
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 use cases, partition keys, consistency, and tenant isolation.
Experience architecting and operating systems on Azure or AWS, with CI/CD and infrastructure as code, and hands-on experience with a durable workflow engine such as Temporal or Durable Task Scheduler.
Experience authoring technical design documents for systems spanning multiple teams, using them to obtain feedback and buy-in before implementation, and having those teams build to the documents.
Clear written and verbal communication for 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 ambiguous customer problems with product managers and data scientists through production operation.
Set the evaluation and guardrail strategy for the product area, including release gates, production signals, and simulations against historical claims before changes ship.
Improve team practices for agentic coding tools by refining specifications, instruction files, hooks, and permission policies, and ensure generated code meets the same review standard before merging.
Design NLP pipelines that transform unstructured claim data into structured, actionable information, selecting appropriate uses for semantic search, classical NLP, and LLMs.
Build and operate durable, event-driven, multi-tenant systems where agents run within deterministic workflows; design failure modes, replay semantics, and cost profiles.
Own tracing and audit for the product area, recording model calls and agent steps so recommendations can be reconstructed and traced to sources by on-call staff and auditors.
Set privacy and security baselines, including tenant isolation, least-privilege access for agents and tools, redaction, retention, and rules for data sent to model providers.
Author design documents for complex systems to obtain feedback and buy-in; review other engineers' designs and code; and mentor engineers in the area.
Participate in a shared on-call rotation for owned systems.