Data Engineer

LVT•American Fork, UT

23h•Remote

About The Position

As Data Engineer, AI, you will play a key role in building and advancing LVT’s data platform — contributing across the full data engineering lifecycle, from ingestion and transformation to semantic modeling and delivery — while also helping build the data infrastructure that powers LVT’s AI initiatives, including RAG pipelines and Snowflake Cortex models. This is a core engineering role with an AI edge: you’ll keep the data platform running with precision and reliability, and you’ll be the person who makes sure our AI systems have the clean, well-structured data they need to perform. LVT is a flexible-first company. This role can be performed remotely, with a preference for candidates who can work from our American Fork, UT office.

Requirements

5+ years building and maintaining production-grade pipelines using SQL, Python, and modern ELT tools such as dbt, Fivetran, or Airflow.
Deep hands-on experience with Snowflake, including performance optimization, dynamic tables, and familiarity with Cortex AI capabilities.
Ability to design and maintain semantic or metrics layers that enforce consistent business logic across the organization.
Working knowledge of RAG architectures and the data patterns — chunking, embedding, retrieval — that support LLM-driven applications.
Strong instinct for reliability — you instrument pipelines with observability and validation from the start.
Comfortable owning work from scoping through production — you define the problem, build the solution, and stand behind the outcome.
Able to work fluidly with engineers, analysts, and non-technical stakeholders, translating ambiguity into clear data solutions.

Responsibilities

Design, build, and maintain scalable ELT pipelines that move data reliably from source systems into a clean, well-governed data platform.
Develop and maintain semantic models that expose consistent, trusted business definitions across reporting and analytics surfaces.
Own data quality — implement validation, monitoring, and alerting frameworks that catch problems before they reach stakeholders.
Optimize Snowflake performance across ingestion, transformation, and storage, including dynamic tables, clustering, and query tuning.
Architect and build the data infrastructure required for RAG applications, including vector storage, chunking strategies, and retrieval pipelines.
Collaborate with AI/ML engineers to support Snowflake Cortex model development with well-structured, context-rich training and inference data.
Partner with analytics engineers, data scientists, and business stakeholders to translate requirements into durable data solutions.
Document data architecture, pipeline design, and modeling decisions to support team knowledge and long-term maintainability.