Senior AI Engineer

We are hiring a Senior AI Engineer to design, build, and operate AI-powered automation across AMPS using hosted large language models (LLMs). This is a hands-on role with end-to-end ownership: you will turn real business problems into secure, production-ready AI features - designing prompts and retrieval pipelines, giving models the tools to act against our systems, and integrating those capabilities directly into our internally built applications.

We work primarily with managed model services (for example, Azure AI) rather than training our own models. Your focus is on getting reliable, accurate results from strong existing models and wiring them safely into how AMPS works - all within a regulated, security-conscious environment where keeping data protected and governed is paramount.

What you'll do

• Design, build, and operate LLM-powered features and automations using hosted model services (e.g., Azure AI / Azure OpenAI) in a secure environment
• Design and iterate on system prompts, prompt templates, and orchestration logic that produce accurate, reliable, and safe outputs
• Build retrieval-augmented generation (RAG) pipelines over proprietary data to keep outputs grounded and accurate
• Integrate LLM capabilities into internally built (homegrown) applications via APIs - including tool/function calling and MCP servers - so models can securely take action against our systems
• Provide models with the tools, context, and integrations they need to automate and speed up real tasks and workflows
• Evaluate and select the right models and services for each use case, balancing quality, latency, cost, and data-security requirements
• Implement evaluation, monitoring, guardrails, and drift detection; continuously improve solutions as requirements change
• Partner closely with application teams, data owners, and AI Innovation leadership to deliver measurable automation gains
• Uphold rigorous data security and governance standards throughout the AI lifecycle
• Other duties as assigned

Requirements

Required

• 5-8+ years of software engineering experience, including hands-on work building and shipping production applications
• Proven experience integrating LLMs or other AI/ML services into real applications via APIs
• Hands-on experience with prompt engineering (system prompts, prompt templates) and retrieval-augmented generation (RAG)
• Strong software engineering skills, with proficiency in Python and the modern LLM tooling ecosystem (RAG, vector databases, orchestration frameworks)
• Experience integrating models with external systems via tool/function calling, including building the services or tools that models call
• Familiarity with LLM evaluation, monitoring, and responsible‑AI / guardrail practices
• A track record of turning ambiguous business problems into working automation
• Bachelor's degree in Computer Science, Engineering, or a related field - or equivalent practical experience
• Ability to work on-site in our Alpharetta, GA office for regular face-to-face collaboration

Preferred

• Experience with Azure AI services (Azure OpenAI, Azure AI Foundry, Azure AI Search) or comparable managed cloud AI platforms
• Experience building agentic workflows and with orchestration frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel)
• Experience with the Model Context Protocol (MCP) - building MCP servers or tools for models to call
• Experience in healthcare or another highly regulated, security-sensitive industry. Healthcare experience is not required, but familiarity with strict data-security governance is a strong plus
• Experience with sensitive-data handling controls in cloud environments

AMPS provides equal employment opportunities to all employees and applicants and prohibits discrimination and harassment of any kind without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state, or local law.