AI Engineer I
Quick Summary
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,
Minimum Bachelor’s degree in a relevant quantitative, technical, engineering, or business-related field, or equivalent combination of education and experience.
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!
Responsibilities
~1 min read
- 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.
- 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.
- 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.
Requirements
~1 min read- Bachelor’s degree in a relevant quantitative, technical, engineering, or business-related field, or equivalent combination of education and experience.
- Typically requires 2 years of relevant experience in AI native analytics
Nice to Have
~1 min read- Masters Degree in a quantitative field
- CS, engineering, math, or stats degree preferred
- Experience with native AI implementations in Insurance industry
- 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.
- 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.
- Daily use of Git and GitHub: branches, PRs, code review
- Works with REST or JSON APIs and reads API documentation without direct supervision
- 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
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
What We Offer
~1 min readLocation & Eligibility
About this job
- Pay per year
- $83,670–$161,815 a year
- 40% below the $205,000 median for Machine Learning Engineer jobs on Jobera (1,121 salaries).
- Posted
- 1 day ago
Listing Details
- Posted
- November 20, 2026
- First seen
- November 21, 2026
- Last seen
- November 21, 2026
Posting Health
- Days active
- 0
- Repost count
- 0
- Trust Level
- 62%
- Scored at
- November 21, 2026
Signal breakdown
Similar Machine Learning Engineer jobs
View all →Stay ahead of the market
Get the latest job openings, salary trends, and hiring insights delivered to your inbox every week.
No spam. Unsubscribe at any time.