AI Engineer (CCC Auto / Agentic)

EvolutionIQ•Chicago, IL

1d•$170,000 - $195,000

About The Position

As an AI Engineer, you will build and ship LLM-powered features and agentic workflows for customers. These features automate routine claim tasks and guide customers through the rest, with accuracy measured in production. Agents run as steps inside deterministic workflows, and privacy and security are baseline design requirements. You will use agentic coding tools to work efficiently while applying system design, security, and debugging expertise, and will own features end to end. You will take features from problem definition with product managers and data scientists through production operation. The role includes building and maintaining NLP pipelines that convert unstructured claim data into structured information, creating durable event-driven services with auditable model traces, and modeling claims data across different database types. You will write technical design documents, participate in a shared on-call rotation, and build privacy and security into your systems. The position offers a salary range of $170,000–$195,000 and is bonus eligible.

Requirements

At least 3 years of professional software engineering experience, including at least one LLM-powered feature shipped and operated in production.
Proficiency in typed, tested, asynchronous Python and TypeScript, with deep expertise in at least one.
Experience designing evaluations for LLM output and shipping guardrails.
Ability to explain how agentic coding tool context is constrained and generated output verified; daily use of Claude Code, Cursor, GitHub Copilot, or similar tools on production work.
Experience building pipelines combining LLMs, semantic search, and classical NLP, including structured output, tool calling, embedding-based retrieval, and an example where a classical technique outperformed an LLM.
Experience with message- or event-driven services, including long-running workflows, retries, idempotent handlers, event-sourced state, and an LLM or agent step in a workflow.
Experience modeling data and developing with relational, document, and graph databases such as PostgreSQL, MongoDB, and Neo4j, including decisions about database fit, partition keys, consistency, and tenant isolation.
Experience building and operating backend services on Azure or AWS, and exposure to a durable workflow engine such as Temporal or the Durable Task Scheduler.
Experience writing technical design documents to obtain team feedback and buy-in before implementation, with the team subsequently building from those documents.
Clear communication for technical and non-technical audiences, and ability to give and receive code review.

Nice To Haves

React and TypeScript experience for delivering full-stack features, especially 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 agent-tool interfaces 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 or what-if simulations that replay historical claims before a change ships.
Exposure to insurance, claims, or automotive repair domains.

Responsibilities

Build and ship LLM-powered features and agentic workflows in Python and TypeScript, from problem scoping with product managers and data scientists through production, and help define performance metrics.
Create evaluations, guardrails, and feedback loops for trustworthy features, and maintain explicit token and latency budgets.
Use agentic coding tools in daily work and review generated code for correctness, security, and design issues before submitting pull requests.
Maintain and extend NLP pipelines that transform unstructured claim data into structured data using semantic search, classical NLP, and LLMs.
Build and operate durable, event-driven services with agents as steps in deterministic workflows, using checkpointed model outputs to avoid repeating completed LLM steps on retries.
Trace model calls and agent steps for reconstruction and auditing, include citations to source documents, and connect tracing to alerts.
Model and query claims data across relational, document, and graph stores.
Design privacy and security controls, including tenant isolation, least-privilege access for agents and tools, and rules for data shared with model providers.
Write technical design documents before significant changes and obtain team feedback and buy-in before implementation.
Participate in a shared on-call rotation for the services built.