Machine Learning Artificial Intelligence Engineer

City National Bank of Florida•Coral Gables, FL

About The Position

City National Bank of Florida is seeking a hands-on Machine Learning / AI Engineer to develop enterprise-grade AI applications, retrieval-augmented generation (RAG) systems, and agentic AI workflows for real banking use cases. These include financial document analysis, credit writing, enterprise knowledge retrieval, risk and fraud prevention, and employee productivity. This is a development-focused role centered on building, testing, and deploying LLM-powered applications rather than pure research or experimentation. The engineer will build production-quality Python applications and backend services, integrate Azure OpenAI and Azure AI Search, and develop RAG pipelines and AI agents using LangChain v1 and LangGraph. The role also involves evaluating AI quality, implementing structured outputs and guardrails, handling sensitive banking information securely, and contributing to containerized deployments, monitoring, troubleshooting, and performance optimization. The engineer will collaborate with senior engineers, AI leadership, business stakeholders, and risk and compliance teams.

Requirements

4–5 years of professional software development experience, with strong hands-on Python proficiency.
Strong knowledge of object-oriented programming, data structures, algorithms, modular design, and clean-code principles.
Experience with FastAPI, REST APIs, Pydantic, SQL, Git, pytest, and debugging.
Practical experience building LLM-powered applications using OpenAI, Azure OpenAI, or comparable model APIs.
Understanding of transformers, embeddings, tokenization, semantic search, and model inference.
Hands-on experience with RAG, including document ingestion, chunking strategies, retrieval, grounding, and evaluation.
Experience with LangChain, LangGraph, or comparable orchestration frameworks.
Experience with prompt design, structured generation, function/tool calling, and output validation.
Ability to measure and improve AI quality rather than relying solely on subjective demonstrations.
Experience with Azure or another major cloud platform.
Familiarity with Docker, CI/CD, application logging, monitoring, and automated testing.
Ability to troubleshoot API failures, retrieval defects, latency, token usage, and model-related errors.
Bachelor's degree in computer science, data science, engineering, applied mathematics/statistics, information systems, or a related quantitative field, or an equivalent combination of education and experience.

Nice To Haves

Direct LangGraph experience is strongly preferred.
Azure cloud experience.
Experience with Azure AI Search, hybrid search, reranking, or vector databases.
Experience building AI agents that call enterprise APIs and tools.
Familiarity with Model Context Protocol (MCP).
Experience with PostgreSQL, Azure Blob Storage, or document-processing pipelines.
Experience in banking, financial services, lending, fraud, or another regulated industry.
Familiarity with responsible AI, data privacy, and auditability.
Master's degree preferred.

Responsibilities

Design, develop, test, and maintain production-quality Python applications for generative AI and applied machine learning.
Build RAG pipelines incorporating document ingestion, parsing, chunking, embeddings, metadata filtering, hybrid search, reranking, and grounded response generation.
Develop AI agents and workflow components using LangChain v1 and LangGraph.
Integrate Azure OpenAI models and Azure AI Search into enterprise AI applications.
Implement structured outputs using Pydantic, schema validation, deterministic business rules, and robust error handling.
Build document validation, financial data extraction, summarization, classification, and analysis components.
Develop automated evaluation datasets and tests to measure retrieval quality, answer correctness, grounding, and regression.
Develop REST APIs and backend services using FastAPI or an equivalent Python framework.
Write unit, integration, and mock-based tests; participate in code reviews and continuous integration.
Implement secure handling of sensitive banking information, prompt-injection defenses, input validation, and appropriate AI guardrails.
Deploy containerized applications and contribute to Azure monitoring, logging, troubleshooting, and performance optimization.
Collaborate with senior engineers, AI leadership, business stakeholders, and risk and compliance teams.