Senior Applied AI Engineer — Production LLM & RAG Apps

Magen Financial LLC; Miami (FL); On-site; USD 140,000 - 190,000; Full time

Job summary

Magen Financial LLC in Miami, FL seeks a Senior Applied AI Engineer to build secure, production-grade AI applications for financial services workflows. This hands-on role focuses on integrating LLMs, RAG, agents, APIs, and enterprise systems—not on model training.

You will collaborate with product, data, and platform teams to deliver scalable solutions, implement guardrails and observability, and turn AI prototypes into reliable production applications.

Qualifications

• 5+ years of software engineering experience.
• Strong C# / .NET and Azure expertise.
• Experience building production APIs and backend services.
• Hands-on experience with Generative AI / LLM integrations.
• Retrieval-Augmented Generation (RAG).
• Experience with SQL, enterprise systems, and cloud-native architectures.
• Ability to turn AI prototypes into reliable production applications.

Responsibilities

• Build AI-powered applications using C#, .NET, and Azure.
• Design and implement RAG pipelines and agentic workflows.
• Integrate LLMs into production systems using APIs, function calling, and tool orchestration.
• Develop backend services and APIs that expose AI capabilities.
• Implement guardrails, validation logic, observability, and human-in-the-loop workflows.
• Collaborate with Product, Data, Platform, and AI teams to deliver secure and scalable solutions.

Skills

C# / .NET

Azure

Back-end APIs

LLM integration

RAG

Security in production

React/TypeScript

Python

Tools

Semantic Kernel

LangChain

Copilot Studio

Azure AI Foundry

Job description

Magen Financial LLC in Miami, FL seeks a Senior Applied AI Engineer to build secure, production-grade AI applications for financial services workflows. This hands-on role focuses on integrating LLMs, RAG, agents, APIs, and enterprise systems—not on model training.

You will collaborate with product, data, and platform teams to deliver scalable solutions, implement guardrails and observability, and turn AI prototypes into reliable production applications.