E

EvolutionIQ

AI-driven SaaS for insurance claims handling

AI Engineer - CCC Auto, Agentic

AI Application Engineering +1Confirmed live in the last 24 hours
Full-timeRemote

About the Job

Requirements

  • At least 3 years of professional software engineering experience, including at least one LLM-powered feature shipped and operated in production.
  • Ability to write typed, tested, asynchronous code in Python and TypeScript, with deep expertise in at least one.
  • Experience designing evaluations for LLM output and shipping guardrails.
  • Experience constraining the context of agentic coding tools and verifying generated output, using Claude Code, Cursor, GitHub Copilot, or a similar tool on production work.
  • Experience with pipelines combining LLMs, semantic search, and classical natural language processing, including structured output, tool calling, embedding-based retrieval, and an example where a classical technique outperformed an LLM.
  • Experience building services with message- or event-driven architectures, including long-running workflows with retries, idempotent handlers, event-sourced state, and an LLM or agent step.
  • Experience modeling data and developing across 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 get team feedback and buy-in before implementation, and having the team build to those documents.
  • Clear written and verbal communication for technical and non-technical audiences, and ability to give and receive code review.

Responsibilities

  • Ship LLM-powered features and agentic workflows in Python and TypeScript, taking work from problem scoping with product managers and data scientists through production traffic, and help set the metrics used to measure the work.
  • Write evaluations, guardrails, and feedback loops to make features trustworthy, and keep them within explicit token and latency budgets.
  • Use agentic coding tools daily and review their output, identifying correctness, security, and design problems before submitting pull requests.
  • Maintain and extend natural language processing pipelines that turn unstructured claim data into structured data, combining semantic search, classical natural language processing, and LLMs.
  • Build and operate durable, event-driven services where agents run as steps in deterministic workflows, with checkpointed model outputs so retries do not repeat completed LLM steps.
  • Trace model calls and agent steps so recommendations can be reconstructed and audited with citations to source documents, and connect tracing to alerts.
  • Model and query claims data across relational, document, and graph stores.
  • Design privacy and security into systems from the outset, including tenant isolation, least-privilege access for agents and their tools, and clear rules for data shared with model providers.
  • Write a technical design document before significant changes and use it to obtain team feedback and buy-in before implementation.
  • Participate in a shared on-call rotation for the services built.

Desired Qualifications

  • Experience with React and TypeScript to deliver full-stack features, especially chat, streaming, and citation-heavy AI experiences.
  • Experience with continuous integration and continuous delivery pipelines and infrastructure as code such as Terraform or Bicep.
  • Experience with agent frameworks such as LangGraph and the Microsoft Agent Framework, and agent tool-access mechanisms including the Model Context Protocol, the Agent2Agent protocol, 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 through a proposed change before release.
  • Exposure to insurance, claims, or automotive repair domains.

About the Company

EvolutionIQ

AI-driven SaaS for insurance claims handling

EvolutionIQ provides AI-driven software for insurers to streamline claims handling across Disability, Workers' Comp, and General Liability. The platform analyzes claim data and medical information, predicts claim paths earlier, automatically routes complex cases to the right expert teams, and guides examiners on needed actions via a SaaS model. It differentiates itself by using AI to understand bodily injury data with precision and to forecast returns-to-work, enabling proactive prioritization unlike traditional manual-rule systems. Its goal is to speed and improve accuracy of claims processing to increase return-to-work outcomes and overall insurer efficiency.

Company size
201-500
Company stage
Acquired
Total funding
$60.3M
Headquarters
New York City, New York
Founded
2019

Recently Posted Jobs

Explore more opportunities at EvolutionIQ

See more jobs