Senior AI Engineer (CCC Auto / Agentic)
$180k - $225k • Remote • Chicago, IL or Remote • Full-time
Posted 16d ago
Job Location
Chicago, IL or Remote
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
As a Senior AI Engineer, you will be responsible for LLM-powered systems and agentic workflows designed to automate routine claim processes and guide customers. These systems require defensible accuracy that can scale with usage and model changes. Agents will operate within deterministic workflows, with privacy and security as core design principles. You will leverage agentic coding tools for rapid development, focusing on system architecture, code quality, security, and in-depth debugging. You will own a product area end-to-end, defining the evaluation standards for its release.
Responsibilities
- Deliver LLM-powered systems in Python and TypeScript, from initial customer problem definition through production operation.
- Establish the evaluation and guardrails strategy for your area, defining release gates, production monitoring signals, and simulation methods.
- Improve the team's use of agentic coding tools by refining specifications, instruction files, hooks, and permission policies.
- Design NLP pipelines to transform unstructured claim data into actionable structured data, selecting appropriate technologies like semantic search, classical NLP, or LLMs.
- Build and operate durable, event-driven, multi-tenant systems where agents function as steps within deterministic workflows, considering failure modes, replay semantics, and cost.
- Implement tracing and audit capabilities for your area to record model calls and agent steps for reconstruction and citation.
- Define and enforce privacy and security baselines for all systems, including tenant isolation, least-privilege access, redaction, retention, and data handling with model providers.
- Author and review technical design documents for complex, cross-team systems, and mentor other engineers.
- Participate in a shared on-call rotation for owned systems.
Requirements
- 6+ years of professional software engineering experience, including architecting and shipping an LLM-powered system to external customers with at least one model or prompt migration.
- Proficiency in Python and TypeScript, including setting team conventions for async models, typing, and testing, with experience profiling and fixing performance issues.
- Experience setting an evaluation and guardrails strategy for a product area, including defining human approval gates and incorporating production corrections into evaluations.
- Demonstrated ability to constrain agentic coding tool context and verify output, with experience using tools like Claude Code, Cursor, or GitHub Copilot.
- Experience designing pipelines that integrate LLMs, semantic search, and classical NLP, including a defensible retrieval design and instances where classical techniques outperformed LLMs.
- Experience designing durable, event-driven systems with deterministic orchestration around non-deterministic model steps, including compensating actions, idempotency, backpressure, and event-sourced replay.
- Experience with data modeling across relational, document, and graph databases (e.g., PostgreSQL, MongoDB, Neo4j), including data type selection and consistency/isolation decisions.
- Experience architecting and operating systems on Azure or AWS, utilizing CI/CD and infrastructure as code, with hands-on experience with workflow engines like Temporal.
- Experience authoring technical design documents for multi-team systems to gain buy-in and guide development.
- Strong written and verbal communication skills for technical and non-technical audiences.
Benefits
- Bonus eligible
