Generative AI Engineer

n \n

• Build, enhance, and support production generative AI applications and web-based AI solutions. \n

• Develop Python backend services and AI integrations using Azure OpenAI, Azure AI Foundry, and related Azure services. \n

• Implement retrieval-augmented generation (RAG) pipelines, including document processing, chunking, embeddings, search, context preparation, and source citations. \n

• Implement agent workflows using tool/function calling, structured outputs, conversation context, error handling, execution limits, and human review where needed. \n

• Integrate AI applications with APIs, enterprise data sources, databases, cloud services, and Model Context Protocol (MCP)-based tools. \n

• Test and evaluate retrieval relevance, answer correctness and grounding, reliability, latency, and cost. \n

• Instrument applications with logging, tracing, and metrics to monitor model calls, retrieval steps, tool execution, errors, and token usage. \n

• Troubleshoot application issues, fix defects, and support deployments and production monitoring. \n

• Participate in code reviews, document implementation decisions, and collaborate with engineering and DevSecOps teams. \n

• Bachelor’s degree in Computer Science, Engineering, or a related field. \n

• 3+ years of technical experience, including developing and supporting production software applications. \n

• 1+ year of hands-on generative AI development, including RAG-based assistants or chatbots. \n

• Experience with Python backend development, including asynchronous APIs, using FastAPI, Pydantic, or comparable tools. \n

• Experience with Azure, including Azure OpenAI, Azure AI Search, and integration with databases and external services. \n

• Hands-on RAG experience with document processing, chunking, embeddings, vector or hybrid search, and citations. \n

• Demonstrated agent workflow experience with tool calling, structured outputs, and context management using PydanticAI, Microsoft Agent Framework, LangGraph, Foundry Agent Service, or similar tools. \n

• Ability to conduct LLM evaluation and troubleshooting using test datasets, logs, and traces to assess quality, latency, and cost. \n

• Experience with Git, code reviews, automated testing, CI/CD, and Agile team delivery. \n

• Must be a U.S. Citizen or Lawful Permanent Resident (Green Card holder). \n

• Ability to obtain and maintain a Public Trust or Suitability/Fitness determination. \n, * Experience with Langfuse, Pydantic Logfire, or similar AI observability tools, and OpenTelemetry. \n

• Experience with advanced RAG techniques, multi-agent workflows, or MCP integrations. \n

• Experience with Docker, Azure deployment services, or frontend development using React, Angular, or TypeScript. \n

• Knowledge of open-source LLM hosting using vLLM, SGLang, or similar frameworks. \n

• Knowledge of LLM fine-tuning and optimization, including PEFT, LoRA/QLoRA, and quantization. \n

• Prior experience supporting CDC or other federal public health programs. \n

n \n

• 401(k) plan with a 4% company match. \n

• Two weeks of paid time off. \n

• Comprehensive medical, dental, and vision insurance. \n

• Ongoing investment in professional growth and development. \n

\n

JRSS is a certified Women-Owned Small Business (WOSB), Small Disadvantaged Business (SDB), and HUBZone business headquartered in Tampa, FL. We specialize in Cloud Services, AI and Machine Learning, Big Data and BI Analytics, Enterprise Resource Planning, IT Project Management, and Staff Augmentation for Federal Civilian agencies (e.g., CDC) and Fortune 500 clients. Our AI engineering teams build secure, production-grade generative AI applications that help public health programs put enterprise knowledge to work.