The Opportunity: The Applied AI Platform Engineer is accountable for building, integrating, testing, deploying, monitoring, and supporting AI Factory platform capabilities that turn AI concepts and prototypes into reliable production services.
This is a hands-on engineering role focused on data pipelines, agent tooling, API integration, model and prompt deployment, evaluation harnesses, observability, CI/CD, infrastructure automation, access controls, cost monitoring, and production support across Databricks, Azure, Python, SQL, and enterprise delivery tooling.
How you will contribute:- Build and operate applied AI platform components, including Lakeflow ingestion jobs, Delta Lake bronze, silver, and gold tables, Unity Catalog governed schemas, vector indexes, document processing pipelines, agent tools, APIs, evaluation jobs, and deployment automation.
- Implement AI enabled workflows using Python, SQL, FastAPI, Databricks Jobs or notebooks, MLflow, Model Serving, Vector Search, Azure AI Document Intelligence, Azure OpenAI Service through approved gateway patterns, and agent frameworks such as Mosaic AI SDK, LangGraph, LangChain, or MCP where appropriate.
- Create and maintain CI/CD pipelines, Terraform modules, automated tests, data quality checks, environment promotion controls, Git based workflows, release packages, and operational runbooks.
- Implement observability for AI workloads, including MLflow traces, evaluation results, model and prompt versions, latency, quality, drift, token and platform cost, error handling, alerting, dashboards, and Azure Monitor or Log Analytics integration.
- Implement production controls, including Entra ID, RBAC, Key Vault secrets, private connectivity, logging, audit evidence, PII handling, retention, confidence thresholds, exception routing, feedback capture, rollback support, and kill switch capability.
- Integrate AI services with core mortgage platforms, SQL Server sources, document repositories, broker communication channels, event backbones such as Azure Service Bus, and user surfaces such as React, Blazor, or other enterprise interfaces.
- Support UAT, parallel runs, defect triage, performance validation, incident analysis, root cause analysis, and controlled handoff from implementation partners to FN support teams.
- Refactor vendor delivered or prototype components into modular, testable, documented, supportable services that First National can maintain and extend.
The experience you need: - Bachelor's degree in computer science, engineering or a related discipline.
- 5 plus years of progressive software engineering, data engineering, platform engineering, cloud engineering, machine learning engineering, or LLMOps experience.
- Strong hands-on experience with Python, SQL, APIs, CI/CD, automated testing, Git based development, cloud services, data platform engineering, and production support.
- Experience with Microsoft Azure, Databricks or comparable platforms, MLflow or similar tooling, model serving, vector search, prompt management, observability, and infrastructure automation is strongly preferred.
- Working knowledge of RAG, document intelligence, agentic workflows, prompt testing, evaluation methods, confidence scoring, red teaming, guardrails, human review controls, and model or prompt drift monitoring.
- Ability to build reliable pipelines, services, jobs, and integrations with attention to performance, cost, resilience, security, privacy, data governance, and operational support.
- Experience supporting UAT, production releases, incident triage, monitoring, root cause analysis, and runbook based operational handoff.
- Experience in financial services, mortgage lending, lending operations, servicing, broker channels, third party partnerships, or regulated technology environments is preferred.
Relationships:External Customers: Works with implementation partners, cloud providers, data and AI platform providers, and specialist vendors on engineering delivery, integration, monitoring, and handoff.
Internal Customers: Partners with the AI Engineering Lead, product teams, engineering teams, data teams, information security, risk and control stakeholders, and business users to turn AI use cases into reliable production capabilities.
Working Environment and Physical Demands Analysis:- Office environment
- Periods of high volume with tight timelines
- Long periods of stationary position/sitting
- Prolonged periods of repetitive movement (i.e. using a keyboard and mouse)
- Long periods of time in viewing a computer screen
- Multi-tasking may include speaking to customers on a telephone call while looking up information on a computer program.
