Senior AI Engineer (CCC Auto / Agentic)

EvolutionIQ•Chicago, IL

2d•$180,000 - $225,000

About The Position

As a Senior AI Engineer, you will own LLM-powered systems and agentic workflows for customers, from defining an ambiguous customer problem with product managers and data scientists through production operation. The systems automate routine claim tasks and guide customers through the rest, so their accuracy must be measurable and defensible as models and usage change. Agents operate as steps within deterministic workflows, with privacy and security treated as design baselines. You will own a product area end to end, set the evaluation bar for releases, and use agentic coding tools while providing architecture, code-quality, security, and debugging expertise. You will develop NLP pipelines that turn unstructured claim data into useful structured information, and build durable, event-driven, multi-tenant systems that combine deterministic orchestration with non-deterministic model steps. You will define evaluation and guardrail strategies, record traces and audits for model calls and agent steps, and establish privacy and security practices for systems in your area. The role also includes authoring and reviewing technical designs, reviewing code, mentoring engineers, and participating in a shared on-call rotation. The stated salary range is $180,000–$225,000, and the position is bonus eligible. A video interview is required; interviews are transcribed and retained for review by CCC and its recruiters. Candidates may not use generative AI or automated assistance during interviews unless the interview team explicitly allows it for a specific exercise.

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 testing in a shared codebase, and profiling and fixing a performance issue.
Experience setting an evaluation and guardrails strategy for a product area, including human-approval requirements and incorporating production corrections into evaluations.
Daily production use of an agentic coding tool such as Claude Code, Cursor, or GitHub Copilot; ability to explain how you constrain its context, verify its output, and examples of changes you 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 model steps, including compensating actions, idempotency, backpressure, and event-sourced replay.
Experience with relational, document, and graph data modeling and development, such as PostgreSQL, MongoDB, and Neo4j, including database selection and partition-key, consistency, and tenant-isolation decisions.
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, gaining feedback and buy-in before implementation, and delivering designs that teams build to.
Clear written and verbal communication with 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 and production operation of LLM-powered systems in Python and TypeScript, from customer problem definition through launch.
Set evaluation and guardrail strategies, including release gates, production signals, and simulations against historical claims.
Improve team practices for agentic coding tools by refining specifications, instruction files, hooks, and permission policies, and reviewing generated code to the team's normal standards.
Design NLP pipelines that convert unstructured claim data into structured information, selecting appropriate uses for semantic search, classical NLP, and LLMs.
Build and operate durable, event-driven, multi-tenant systems with agents embedded as steps in deterministic workflows; design failure modes, replay semantics, and cost profiles.
Own tracing and auditing so model calls and agent steps are recorded and recommendations can be reconstructed and traced to sources.
Set privacy and security baselines, including tenant isolation, least-privilege access, redaction, retention, and rules for data sent to model providers.
Write design documents for complex systems, review other engineers' designs and code, and mentor engineers in the product area.
Participate in a shared on-call rotation for owned systems.