Data & AI Platform Architect

ProviderTrust•Nashville, TN

2h•Hybrid

About The Position

ProviderTrust is seeking a senior, hands-on engineer to design and build the company's data warehouse and data lake foundation. This role will also lead the implementation of large language model (LLM) capabilities across internal tooling and customer-facing products. This is a greenfield, high-ownership position where the individual will influence architecture, platform, and tooling, establishing standards for future development. The ideal candidate is proficient in architecting scalable data pipelines and designing secure, production-grade LLM integrations, including retrieval-augmented generation (RAG), prompt/response governance, and model evaluation.

Requirements

7+ years of experience in data engineering, with at least 3 years designing or owning a production data warehouse or data lake architecture from the ground up.
Hands-on experience building and shipping LLM-powered features in production (RAG, agentic workflows, embeddings/vector search, or fine-tuning).
Strong SQL and Python skills; experience with modern ELT/orchestration tools (dbt, Airflow, Spark, or equivalent).
Deep familiarity with at least one major cloud data platform (Snowflake, Databricks, BigQuery, Redshift, or Azure Synapse).
Practical experience with major LLM provider APIs (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock) and LLM application frameworks (LangChain, LlamaIndex, or similar).
Solid understanding of data security, access control, and privacy practices for sensitive or regulated data.
Track record of making and documenting architecture decisions independently, with minimal oversight.
Strong written and verbal communication skills; able to explain technical tradeoffs to non-technical stakeholders.
Experience defining systems of record across CRM, ERP, and support platforms, and integrating systems such as Salesforce, NetSuite, HubSpot, Zendesk, or Jira.
Strong data modeling skills (dimensional modeling, medallion or equivalent) and experience standing up a data catalog and data quality testing.

Nice To Haves

Experience in a regulated industry (healthcare, financial services, or compliance-driven environments).
Experience fine-tuning or self-hosting open-source LLMs (e.g., Llama, Mistral) for cost or data-residency reasons.
Prior experience building a data or AI function from scratch at a startup or scale-up.
Familiarity with MLOps/LLMOps tooling for evaluation, monitoring, and guardrails (e.g., MLflow, Weights & Biases, Ragas, or custom eval harnesses).
Experience with infrastructure-as-code and containerized deployments (Terraform, Docker, Kubernetes).
Prior people-leadership or technical-lead experience, if the role is expected to grow a team.

Responsibilities

Design, build, and own the enterprise data warehouse and data lake (or lakehouse) architecture from the ground up, including ingestion, storage, transformation, and serving layers.
Evaluate and select the core platform and supporting orchestration/ETL tooling based on cost, scale, and team skillset.
Build reliable, well-documented pipelines that consolidate data from operational systems, third-party sources, and application logs into a single source of truth.
Establish data modeling standards (e.g., dimensional modeling, medallion architecture) and enforce data quality, lineage, and observability practices.
Implement role-based access controls, encryption, and data retention policies appropriate for sensitive and regulated data.
Architect and implement internal LLM tooling (e.g., knowledge-base search, analyst copilots, internal chat assistants) that draws on the data warehouse/lake as a grounded knowledge source.
Design and ship customer-facing (external) LLM-powered features, ensuring reliability, latency, and cost are production-ready at scale.
Build retrieval-augmented generation (RAG) pipelines, including chunking, embedding, and vector search, to ground model outputs in company and customer data.
Stand up evaluation, monitoring, and guardrail frameworks to catch hallucination, data leakage, and quality regressions before and after release.
Own vendor and model strategy across proprietary APIs (OpenAI, Anthropic, Azure OpenAI, Bedrock) and, where appropriate, self-hosted or fine-tuned open-source models.
Partner with security and compliance stakeholders to ensure LLM features meet data privacy, auditability, and regulatory requirements (e.g., PII handling).
Define and document architecture decisions, data governance policies, and AI usage guidelines for the broader engineering organization.
Act as the internal subject-matter expert on data platform and applied AI/LLM strategy, advising product, engineering, and leadership on feasibility and roadmap.
Mentor engineers as the team grows, and help recruit and evaluate future data/AI hires.
Manage costs and performance across cloud data and AI infrastructure through capacity planning and optimization.