Markel AI Automation Intern

Markel•Los Angeles, CA

3d•$24 - $29

About The Position

Markel is hiring an AI Automation Intern to build and improve practical tools that reduce repetitive work for underwriters, claims handlers, and operations teams. Projects include AI-assisted underwriting workbenches, automated email flows, and integrations between existing systems. Work may progress from a discussion with a business leader to a working proof of concept in days, followed by testing, hardening, and handoff. As the second person on this work, the intern will learn about specialty insurance and the safe use of AI in a regulated business.

Requirements

Bachelor's degree.
Working skill in at least one programming language, ideally Python or JavaScript, demonstrated through coursework, an internship, or personal projects.
Basic understanding of web APIs, including HTTP requests, JSON, and authentication.
Strong Excel skills, including lookups, pivot tables, and formulas, and comfort working with large data sets.
Clear writing and the ability to explain technical work to people who do not code.
Curiosity about AI and the habit of checking AI answers rather than trusting them without verification.
Good judgment when handling customer and broker information, including asking before sharing or sending it.
Business acumen.
US work authorization; Markel does not provide visa sponsorship for this position now or in the future.

Responsibilities

Build and improve proof-of-concept tools, including browser-based workbenches for underwriters to review submissions, price risks, and produce quotes.
Connect systems through APIs, including sending requests, handling authentication and tokens, mapping returned data, and managing errors.
Write Python scripts to transform spreadsheets, PDFs, and Word documents into clean data and produce finished documents from data.
Build and maintain Power Automate flows, SharePoint lists, and Copilot Studio agents for email triage, document review, and reminders.
Develop prompts and extraction schemas for large language models, and create test sets to evaluate accuracy and cost.
Test tools before use with automated browser checks, unit tests, and comparisons against source data.
Deploy tools on Databricks while managing access, secrets, and cost.
Write setup notes, runbooks, user guides, and change logs so others can maintain projects.
Attend meetings with underwriters and business leaders, capture their needs, and translate them into clear requirements.