Join an amazing team that is consistently recognized for our achievements and culture, including our most recent Forbes award of being one of America's Best Midsize Employers for 2026!
Position Summary:
We're hiring an Artificial Intelligence (AI) Engineer I to help build and maintain our metric intelligence platform: the agents, skills, and backend services that turn governed business metrics into automated analysis for teams across the company.
This position is part of the Enterprise Data Services Division--we own the company's metric definitions, the semantic layer that serves them, and an AI-powered analytics platform built on top. Metric logic lives in version-controlled code; agents and applications read from it rather than reinventing it.
This is an engineering role, not a prompt-writing role. Most of the platform's skills are deterministic Python, with AI agents orchestrating them. You'll spend more time making things correct, tested, and reliable than making them clever.
Geo-Salary Information
An in-person interview may be required during the hiring process
State specific pay scales for this role are as follows:
$83,670.00 to $161,815.00 (NJ, NY, WA, HI, AK, MD, CT, RI, MA)
$76,064 to $147,104 (NV, OR, AZ, CO, WY, TX, ND, MN, MO, IL, WI, FL, GA, MI, OH, VA, PA, DE, VT, NH, ME)
$68,457 to $132,394 (UT, ID, MT, NM, SD, NE, KS, OK, IA, AR, LA, MS, AL, TN, KY, IN, SC, NC, WV)
In CA: Typical hiring range is $98,194 - $153,428
The expected base salary for this position will vary depending on a number of factors, including relevant experience, skills and location.
ResponsibilitiesEssential Job Functions:
Agents and skills management
- Build, test, and maintain the Python skills and AI agents that run on the platform.
- Keep a clean skills catalog: versioning, documentation, ownership, and retiring skills that are no longer used.
- Build evaluation and regression checks (test sets, validators, output-format rules) so agent quality is consistent from run to run.
- Monitor agent usage, cost, and failures, and fix the root cause rather than the symptom.
Platform backend maintenance
- Maintain the platform's agent runtime, built on a TypeScript agent framework (Mastra): agent workflows, tool definitions, memory, and model configuration.
- Maintain MCP (Model Context Protocol) servers and connectors that link agents to the warehouse, semantic layer, BI tools, and other company systems.
- Keep the platform's API services, scheduled jobs, and data pipelines healthy; handle framework, SDK, and model version upgrades.
- Triage and resolve failed jobs, broken connectors, data-quality alerts, and user-reported issues.
- Improve CI/CD, logging, and monitoring so problems surface before users find them.
- Write runbooks so any teammate can operate the platform.
Data foundation (working knowledge)
- Understand how the gold data layer and semantic models feed the platform, and make small, reviewed changes to them.
- Work with the metric tree, the map of how business metrics drive each other, to connect new metrics and their relationships to the platform.
- Trace a number from the platform back to its source data when something looks wrong.
Qualifications
Education:
Minimum
- Bachelor’s degree in a relevant quantitative, technical, engineering, or business-related field, or equivalent combination of education and experience.
Preferred
- Masters Degree in a quantitative field
- CS, engineering, math, or stats degree preferred
Experience:
Minimum
- Typically requires 2 years of relevant experience in AI native analytics
Preferred
- Experience with native AI implementations in Insurance industry
Knowledge and Skills:
Programming
- Python: writes, tests, and debugs modular code independently. Deterministic Python
- TypeScript/JavaScript: can read and change an existing backend codebase. Mastra is TS-based, so this is required.
- SQL: joins, aggregations, and window functions against a warehouse; can sanity-check a metric's output.
LLM and agent fundamentals
- Has built at least one working LLM application end to end, such as a tool-calling agent, a RAG app, or an MCP server. A shipped side project counts.
- Understands prompts versus tools versus retrieval, context limits, and why agent output is nondeterministic.
- Has an instinct for evaluation: tests agent output against expected answers instead of eyeballing it.
Engineering hygiene
- Daily use of Git and GitHub: branches, PRs, code review
- Works with REST or JSON APIs and reads API documentation without direct supervision
Data and domain basics (concepts only)
- Understands what a semantic layer, dimension, and metric are, and how they differ from raw tables
- Can read a dbt model and YAML config and follow the lineage
Why choose a career at Mercury?
At Mercury, we have been guided by our purpose to help people reduce risk and overcome unexpected events for more than 60 years. We are one team with a common goal to help others. Everyone needs insurance and we can’t imagine a world without it.
Our team will encourage you to grow, make time to have fun, and work together to make great things happen. We embrace the strengths and values of each team member. We believe in having diverse perspectives where everyone is included, to serve customers from all walks of life.
We care about our people, and we mean it. We reward our talented professionals with a competitive salary, bonus potential, and a variety of benefits to help our team members reach their health, retirement, and professional goals.
Learn more about us here: https://www.mercuryinsurance.com/about/careers
#LI-DS1
#LI-Remote
Perks and BenefitsWe offer many great benefits, including:
- Competitive compensation
- Flexibility to work from anywhere in the United States for most positions
- Paid time off (vacation time, sick time, 9 paid Company holidays, volunteer hours)
- Incentive bonus programs (potential for holiday bonus, referral bonus, and performance-based bonus)
- Medical, dental, vision, life, and pet insurance
- 401 (k) retirement savings plan with company match
- Engaging work environment
- Promotional opportunities
- Education assistance
- Professional and personal development opportunities
- Company recognition program
- Health and wellbeing resources, including free mental wellbeing therapy/coaching sessions, child and eldercare resources, and more
Mercury Insurance is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, status as a protected veteran, or any other characteristic protected by federal, state, or local law.
Mercury is committed to working with and providing reasonable accommodations for qualified individuals with disabilities who need assistance with the application and/or employment consideration process. If you require an accommodation, you may contact us by sending an e-mail to [email protected]. Please include your name, contact information, and a description of your requested accommodation in your message.
Pay RangeUSD $83,670.00 - USD $161,815.00 /Yr.Skills Required
- Bachelor's degree in a relevant quantitative, technical, engineering, or business-related field, or equivalent combination of education and experience
- Typically 2 years of relevant experience in AI-native analytics
- Ability to write, test, and debug modular deterministic Python independently
- Ability to read and modify an existing TypeScript or JavaScript backend codebase
- SQL proficiency including joins, aggregations, and window functions
- Experience building at least one working LLM application end to end, such as a tool-calling agent, RAG application, or MCP server
- Understanding of prompts, tools, retrieval, context limits, and nondeterministic agent output
- Ability to evaluate agent output against expected answers
- Daily Git and GitHub usage, including branches, pull requests, and code review
- Experience working with REST or JSON APIs and reading API documentation independently
- Understanding of semantic layers, dimensions, and metrics
- Ability to read dbt models and YAML configuration and follow data lineage
- Master's degree in a quantitative field
- Degree in computer science, engineering, mathematics, or statistics
- Experience with native AI implementations in the insurance industry
Mercury Insurance Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Mercury Insurance and has not been reviewed or approved by Mercury Insurance.
-
Healthcare Strength — Core medical coverage spans multiple plan types alongside dental and vision, with employer HSA funding, mental‑health access, and wellness incentives. These offerings indicate a well‑rounded health and wellbeing package.
-
Retirement Support — A 401(k) with company match and automatic enrollment indicates structured retirement support. A defined vesting approach further underscores consistent long‑term savings assistance.
-
Leave & Time Off Breadth — Time‑off offerings cover vacation, sick time, paid holidays, and standard leaves such as bereavement, military, and family medical. The menu provides baseline coverage across key leave categories, with accrual improving over tenure.
Mercury Insurance Insights
What We Do
At Mercury, we have been guided by our purpose to help people reduce risk and overcome unexpected events for more than 60 years. We are one team with a common goal to help other others. Everyone needs insurance and we can’t imagine a world without it. Our team will encourage you to grow, make time to have fun, and work together to make great things happen. We are an award-winning company, and we owe that to our amazing team! We care about our people, and we mean it. We reward our talented professionals with a competitive salary, bonus potential, and a variety of benefits to help our team members reach their health, retirement, and professional goals. Mercury was founded in 1961 by George Joseph, Mercury’s Founder and Chairman. Back in the 50s, everyone paid the same rate, regardless of their driving record. Joseph decided he could create a new system by developing an insurance company that used different factors to create fair and equitable rates for a variety of drivers. “We called our company Mercury, because I wanted us to be fast and nimble, just like the Roman God of business and merchants,” says Joseph. “He was also responsible for delivering good news to people on Earth, which is exactly what we do for Mercury customers every day.” We, Mercury Insurance (NYSE-MCY), are a leading independent broker and agency writer of automobile insurance in California and one of the fastest growing automobile insurers in the nation. We were ranked as the fourth largest private passenger automobile insurer in California, with over $4.5 billion in total assets, 4,500 team members, and 8,000 independent agents. We started by providing comprehensive coverage options for auto and expanded our offerings into home, condo, renters, and business insurance, as well as mechanical protection. We operate through a network of local, independent agents in Arizona, California, Florida, Georgia, Illinois, Nevada, New Jersey, New York, Oklahoma, Texas and Virginia.









