Prompt Architect for GenAI & RAG Systems (Hybrid)

Moonfire; Irving (TX); Hybrid; USD 110,000 - 140,000; Full time

Job summary

Moonfire in Irving, TX is seeking a Prompt Engineer to design, test, and optimize prompts for large language models, ensuring outputs are accurate, safe, and useful. You will craft system instructions, develop context guidelines, and support RAG workflows, while collaborating with data scientists and software engineers on reliable AI solutions.

This hybrid role requires strong communication, knowledge of tokenization, embeddings, APIs such as OpenAI, and experience with frameworks like LangChain

Qualifications

• Understanding of tokenization, context windows, and APIs (OpenAI, Anthropic, or Azure OpenAI).
• GenAI concepts: foundation models, LLMs, embeddings, tokenization.
• Hands-on prompt/context engineering and RAG experience.
• Knowledge graphs and Graph RAG experience.
• Exposure to agentic AI, tool-using agents, and frameworks such as ADK, LangGraph, CrewAI, or OpenAI Agents SDK.
• Awareness of tool/function calling, MCP, A2A, memory and guardrails.
• Experience with GenAI APIs (OpenAI, Gemini, Claude) and orchestration frameworks (LangChain, LlamaIndex).
• Familiarity with Docker, Git and AI compliance/privacy.

Responsibilities

• Design, test, and optimize prompts for chatbots, copilots, and RAG systems.
• Support context engineering, prompt engineering, and RAG workflows with embeddings and semantic search.
• Assist with deployment, monitoring, data preprocessing, API development, and code reviews.
• Test model outputs for accuracy, safety, latency, and token cost.

Skills

AI & LLM familiarity

Python for GenAI

Context windows

Tokenization

RAG experience

Knowledge graphs

MCP exposure

LangChain

LangGraph

Tools

LangGraph

CrewAI

OpenAI API

LlamaIndex

Docker

Git

Job description

Moonfire in Irving, TX is seeking a Prompt Engineer to design, test, and optimize prompts for large language models, ensuring outputs are accurate, safe, and useful. You will craft system instructions, develop context guidelines, and support RAG workflows, while collaborating with data scientists and software engineers on reliable AI solutions.

This hybrid role requires strong communication, knowledge of tokenization, embeddings, APIs such as OpenAI, and experience with frameworks like LangChain