AI Engineer I

Mercury Insurance Services, LLC•, CA
•$68,457 - $161,815•Remote

About The Position

The AI Engineer I will help build and maintain Mercury’s metric intelligence platform, including the agents, skills, and backend services that turn governed business metrics into automated analysis. The role is part of the Enterprise Data Services Division, which manages the company’s metric definitions, semantic layer, and AI-powered analytics platform. Metric logic is maintained in version-controlled code, which agents and applications use rather than recreate. This is an engineering role focused on correctness, testing, and reliability. Most platform skills are deterministic Python, with AI agents orchestrating them. The engineer will also maintain TypeScript-based agent runtime components and connectors, support platform services and data pipelines, and work with the gold data layer and semantic models. The position is open to candidates working from anywhere in the United States for most positions. An in-person interview may be required during the hiring process. Salary varies by location and factors such as experience and skills. Listed ranges include $83,670–$161,815 in specified states, $76,064–$147,104 in another group of states, $68,457–$132,394 in another group, and a typical California hiring range of $98,194–$153,428. The overall listed pay range is $83,670–$161,815 per year.

Requirements

  • Bachelor’s degree in a relevant quantitative, technical, engineering, or business-related field, or an equivalent combination of education and experience.
  • Typically requires 2 years of relevant experience in AI-native analytics.
  • Able to write, test, and debug modular deterministic Python code independently.
  • Able to read and modify an existing TypeScript/JavaScript backend codebase; TypeScript is required because Mastra is TypeScript-based.
  • Able to use SQL joins, aggregations, and window functions against a warehouse and sanity-check metric outputs.
  • Has built at least one working LLM application end to end, such as a tool-calling agent, RAG app, or MCP server; a shipped side project counts.
  • Understands prompts versus tools versus retrieval, context limits, and why agent output is nondeterministic.
  • Uses evaluation to test agent output against expected answers rather than relying on visual inspection.
  • Daily use of Git and GitHub, including branches, pull requests, and code review.
  • Works with REST or JSON APIs and can read API documentation without direct supervision.
  • Understands semantic layers, dimensions, and metrics and how they differ from raw tables.
  • Can read a dbt model and YAML configuration and follow lineage.

Nice To Haves

  • Master’s degree in a quantitative field.
  • Degree in computer science, engineering, mathematics, or statistics.
  • Experience with native AI implementations in the insurance industry.

Responsibilities

  • Build, test, and maintain Python skills and AI agents that run on the platform.
  • Maintain the skills catalog, including versioning, documentation, ownership, and retiring unused skills.
  • Build evaluation and regression checks, including test sets, validators, and output-format rules, to maintain consistent agent quality.
  • Monitor agent usage, cost, and failures, and address root causes.
  • Maintain the platform’s agent runtime built on the Mastra TypeScript agent framework, including workflows, tool definitions, memory, and model configuration.
  • Maintain MCP servers and connectors linking agents to the warehouse, semantic layer, BI tools, and other company systems.
  • Keep API services, scheduled jobs, and data pipelines healthy, and 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 teammates can operate the platform.
  • Understand how the gold data layer and semantic models feed the platform, and make small, reviewed changes to them.
  • Use the metric tree to connect new metrics and their relationships to the platform.
  • Trace platform numbers back to source data when issues arise.

Benefits

  • Competitive compensation
  • Potential bonus and incentive programs, including possible holiday, referral, and performance-based bonuses
  • Paid time off, including vacation time, sick time, nine paid company holidays, and volunteer hours
  • Medical insurance
  • Dental insurance
  • Vision insurance
  • Life insurance
  • Pet insurance
  • 401(k) retirement savings plan with company match
  • Education assistance
  • Professional and personal development opportunities
  • Health and wellbeing resources, including free mental wellbeing therapy/coaching sessions and child and eldercare resources
  • Company recognition program
  • Promotional opportunities
  • Flexibility to work from anywhere in the United States for most positions
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service