AI Solutions Analyst

At doTERRA we encourage all employees to seek out opportunities that will expand their skill set. We strive to help achieve personal career goals by providing opportunities of growth and movement throughout the company.

The AI Solutions Analyst I helps build, deploy, and continuously improve AI-powered data solutions that enable employees to ask business questions and perform ad hoc analysis using natural language. Working closely with the Data Warehousing team and business stakeholders, this role configures and optimizes AI agents within Snowflake, translates business requirements into effective agent experiences, tests and evaluates agent performance, and improves the quality and usefulness of agent responses over time. This is an early-career technical analytics role at the intersection of data, artificial intelligence, and business enablement. Its primary focus is making enterprise AI agents accurate, useful, reliable, governed, and accessible to business users rather than developing production software or owning core data warehouse models. Work location: This position is based at doTERRA's Pleasant Grove, Utah campus and requires full-time, on-site presence.

AI Agent Development & Configuration Build and configure internal AI agents that help employees interact with approved enterprise data through natural language. Define and refine agent instructions, context, tools, workflows, guardrails, and expected response behaviors. Configure agents to use approved Snowflake data assets, Cortex Analyst semantic views, and other governed resources as appropriate. Create and maintain evaluation sets that include representative questions, expected outcomes, edge cases, and known limitations. Diagnose inaccurate, incomplete, unsupported, or inconsistent responses and iterate on configurations to improve results. Evaluate emerging Snowflake AI and agent capabilities and recommend where they can strengthen doTERRA's internal AI ecosystem. Agent Quality & Continuous Improvement Establish repeatable methods for evaluating response correctness, relevance, groundedness, consistency, reliability, and usability. Review agent interactions, evaluation results, and user feedback to identify recurring failure patterns and improvement opportunities. Test and document changes to instructions, tools, and configurations before broader deployment. Partner with Data Warehousing team members when agent performance reveals gaps in source data, business definitions, semantic resources, or access patterns. Help develop standards, documentation, and lifecycle practices for creating, releasing, monitoring, and maintaining enterprise AI agents. Follow applicable data governance, security, privacy, and responsible AI requirements, escalating risks or control gaps when identified. Business Requirements & Solution Design Meet with business leaders and end users to understand common questions, workflows, terminology, metrics, and decision-making needs. Translate business requirements into clear agent use cases, acceptance criteria, representative questions, and expected behaviors. Identify which questions and workflows are appropriate for AI-enabled self-service analytics and clarify boundaries for out-of-scope or higher-risk requests. Work with technical partners to confirm that required data is available, governed, defined consistently, and structured for the intended use case. Validate solutions with business stakeholders and incorporate their feedback into prioritized improvements. Adoption & Enablement Support the rollout of AI agents across business functions through pilots, demonstrations, training, and practical usage guidance. Help users learn how to ask effective questions, interpret results, and recognize when additional validation is needed. Document agent capabilities, limitations, intended use cases, data coverage, and known behaviors in clear language. Gather structured feedback, maintain an improvement