1 day ago
Remote, United StatesEntry Level

Base Salary

$84k - $162k/yr

Responsibilities

  • Build, test, and maintain deterministic Python skills and AI agents for the metric intelligence platform.
  • Manage the skills catalog through versioning, documentation, ownership, and retirement of obsolete skills.
  • Create evaluation and regression checks, including test sets, validators, and output-format rules, to maintain consistent agent quality.
  • Monitor agent usage, costs, and failures and resolve underlying causes.
  • Maintain the TypeScript-based Mastra agent runtime, 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; perform framework, SDK, and model upgrades.
  • Triage failed jobs, broken connectors, data-quality alerts, and user-reported issues.
  • Improve CI/CD, logging, and monitoring and write runbooks for platform operations.
  • Understand and make small reviewed changes to the gold data layer and semantic models, connect metrics through the metric tree, and trace metrics to source data.

Requirements

  • Bachelor’s degree in a relevant quantitative, technical, engineering, or business-related field, or an equivalent combination of education and experience.
  • Typically requires at least 2 years of relevant experience in AI-native analytics.
  • Master’s degree and a computer science, engineering, mathematics, or statistics degree are preferred.
  • Ability to independently write, test, and debug modular Python code.
  • Ability to read and modify an existing TypeScript/JavaScript backend codebase; TypeScript is required for the Mastra framework.
  • Proficiency with SQL joins, aggregations, and window functions for warehouse analysis and metric validation.
  • Experience building at least one working end-to-end LLM application, such as a tool-calling agent, RAG application, or MCP server; a shipped side project counts.
  • Understanding of prompts, tools, retrieval, context limits, nondeterministic agent output, and agent-output evaluation.
  • Daily experience using Git and GitHub, including branches, pull requests, and code review.
  • Ability to work with REST or JSON APIs and read API documentation independently.
  • Understanding of semantic layers, dimensions, metrics, raw tables, dbt models, YAML configuration, and data lineage.
  • Experience with native AI implementations in the insurance industry is preferred.

Benefits

  • Competitive base compensation with incentive bonus programs, including potential holiday, referral, and performance-based bonuses.
  • Flexibility to work from anywhere in the United States for most positions; an in-person interview may be required.
  • Paid time off, including vacation, sick time, nine paid company holidays, and volunteer hours.
  • Medical, dental, vision, life, and pet insurance.
  • 401(k) retirement savings plan with company match.
  • Education assistance, professional and personal development opportunities, promotional opportunities, and a company recognition program.
  • Health and wellbeing resources, including free mental wellbeing therapy or coaching sessions and child and eldercare resources.
Mercury Insurance Services, LLC

About Mercury Insurance Services, LLC

1,001-5,000 employees

Mercury Insurance Services, LLC sells personal auto, homeowners, renters, and related coverage (umbrella, condo, business auto, and mechanical breakdown) to consumers, primarily through independent agents. The company generates revenue from underwriting and premiums on property-and-casualty policies and is publicly traded on the NYSE (ticker: MCY). Founded in 1962 and headquartered in Brea, California, it is a major writer of auto insurance in California and operates in multiple U.S. states.

Contact me