CCC Intelligent Solutions Inc. is seeking a Senior AI Engineer to take ownership of LLM-powered systems and agentic workflows from design through production operations. The role focuses on accuracy-evaluable automation, deterministic orchestration, privacy and security baselines, tracing and audit, and long-term system reliability.
Responsibilities
- Own delivery of LLM-powered systems written in Python and TypeScript, translating an ambiguous customer problem into a scoped solution with product managers and data scientists, and carrying the work through production operations.
- Define and execute evals and guardrails strategy for your product area, including release gates, production signals the team monitors, and simulation of changes against historical claims before deployment.
- Raise standards for team execution using agentic coding tools by improving specifications, instruction files, hooks, and permission policies, and applying the same review standard to generated code prior to merge.
- Design NLP pipelines that convert unstructured claim data into structured outputs customers can use, selecting between semantic search, classical NLP, and LLM-based approaches.
- Build and operate durable, event-driven, multi-tenant systems where agents operate as steps inside deterministic workflows, including failure mode design, replay semantics, and cost profiling prior to load.
- Own tracing and audit for your scope by recording every model call and agent step so recommendations can be reconstructed and cited to sources for on-call and audits.
- Own how claims data is modeled and handled across relational, document, and graph stores.
- Set the privacy and security baseline for systems in your area, covering tenant isolation, least-privilege access for agents and tools, redaction, retention, and what personal and medical data may reach a model provider.
- Author design documents for complex systems to obtain feedback and alignment, review other engineers’ designs and code, and mentor engineers within your scope.
- Participate in a shared on-call rotation for the systems you own.
Requirements
- 6+ years of professional software engineering experience, including an LLM-powered system you architected, shipped to external customers, and carried through at least one model or prompt migration.
- Strong Python and TypeScript experience, including setting team conventions (async model, typing strictness, and test strategy), plus profiling and resolving performance issues in a shared codebase.
- Proven ability to design evals and guardrails for a product area built by others, including human approval points and how production corrections re-enter the eval loop.
- Clear experience constraining agentic coding tool context and verifying outputs in production, including daily usage of tools such as Claude Code, Cursor, GitHub Copilot, or similar, and knowledge of changes you reverted and the rationale.
- Pipeline experience blending LLMs, semantic search, and classical NLP, including a defendable retrieval design and evidence of a classical approach outperforming an LLM on cost, latency, or reliability.
- Experience building durable, event-driven systems with deterministic orchestration around non-deterministic model steps, including compensating actions, idempotency, backpressure, and event-sourced replay.
- Ability to make and defend production datastore choices among PostgreSQL, MongoDB, Neo4j, SQL Server, and Cosmos DB, including data model, partition key, consistency, and tenant isolation decisions.
- Experience architecting and operating on Azure or AWS, including CI/CD and infrastructure as code, and hands-on work with a durable workflow engine such as Temporal or the Durable Task Scheduler.
- Experience authoring technical design documents for systems spanning multiple teams, gaining feedback and buy-in before building, and enabling those teams to implement accordingly.
- Ability to write and discuss technical decisions with both technical and non-technical audiences, including translating customer problems and explaining trade-offs.
Technologies
Python, TypeScript, Claude Code, Cursor, GitHub Copilot, PostgreSQL, MongoDB, Neo4j, SQL Server, Cosmos DB, Azure, AWS, CI/CD, infrastructure as code, Temporal, Durable Task Scheduler, LangGraph, Microsoft Agent Framework, Model Context Protocol (MCP), Agent2Agent (A2A) protocol, LangSmith, Arize, Braintrust, OpenTelemetry, React, A/B tests
Benefits
- 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 agent frameworks such as LangGraph and the Microsoft Agent Framework, and with how agents reach tools via Model Context Protocol (MCP), Agent2Agent (A2A) protocol, command-line tools, and microservices.
- Experience with LLM observability and evaluation tooling such as LangSmith, Arize, or Braintrust, plus tracing with OpenTelemetry.
- Experience designing A/B tests for AI features.
- Exposure to the insurance, claims, or automotive repair domains.
What Success Looks Like
- Within the first six months, every model change in your area is gated by evals you designed, regressions are caught before customers are impacted, and you can report an accuracy number that has held or moved.
- You address ambiguity by turning high-stakes problems into a roadmap, a shipped system, and measurable outcomes.
- You leverage agentic coding tools to deliver more than headcount alone by using specifications and reviews that support production-grade output.
- You build systems with understood failure modes, with traces that clarify where a failure occurs when it does happen.
- Privacy and security reviews for your systems find no issues beyond what was already designed.
- You establish standards that persist beyond individual projects.
- Engineers you mentor ship LLM-powered features with evals and guardrails in place without requiring your direct involvement.
- You collaborate with product managers, data scientists, and customer teams to align on a single agreed scope and can defend positions through discussion.
- You align with ambitious, collaborative, and empathetic values, especially on problems where answers are measured rather than argued.
Interview Policy & Privacy Notice
- A video interview is required for this position. Video interviews are transcribed.
- Transcriptions are retained and may be reviewed by CCC and our 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.
- Our Job Applicant Privacy Notice is available HERE.
Location
Chicago, IL (onsite)
