AI Prompt Engineer

Moonfire; New Jersey; On-site; USD 110,000 - 170,000; Full time

Job summary

Moonfire is seeking an AI Prompt Engineer to design, optimize, and evaluate prompts for Generative AI and LLMs. The role collaborates with stakeholders, data scientists, and product teams to improve accuracy, safety, and user experience across enterprise use cases.

The position requires hands-on experience with OpenAI/Claude, Python, and frameworks like LangChain or LlamaIndex. Onsite work in Whippany, NJ is required, with strong emphasis on governance and documentation.

Qualifications

• Design, test and refine prompts for LLMs in enterprise use cases.
• Familiarity with prompt patterns and assessment of outputs.
• Hands-on AI development with Python and related frameworks.

Responsibilities

• Design, develop, test, and refine prompts for LLMs used in enterprise apps.
• Create and enforce prompt engineering best practices.
• Evaluate outputs and optimize prompts for safety and relevance.
• Develop prompt libraries, chains, and AI agent workflows.
• Collaborate with data scientists, AI engineers, and product teams.

Skills

Generative AI & LLMs

Prompt engineering

OpenAI/ Claude experience

Python

LangChain / LangGraph / LlamaIndex

Vector databases (Pinecone)

RAG architectures

Prompt patterns (Zero-shot, Few-shot,

Documentation & governance

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Pinecone

Job description

Job Title: AI Prompt Engineer

Location: Whippany , NJ ( 3 days onsite)

Fulltime

OPT is fine

Role Overview

We are seeking an innovative and detail-oriented AI Prompt Engineer to design, optimize, and evaluate prompts for Generative AI and Large Language Model (LLM) applications. The ideal candidate will work closely with business stakeholders, data scientists, AI engineers, and product teams to develop high-quality prompts that improve AI accuracy, reliability, and user experience across enterprise use cases.

Key Responsibilities

• Design, develop, test, and refine prompts for LLMs such as GPT /Claude .
• Create prompt engineering best practices for enterprise applications.
• Evaluate model outputs and continuously optimize prompts for accuracy, relevance, safety, and performance.
• Develop prompt libraries, prompt chains, and AI agent workflows.
• Work with RAG (Retrieval Augmented Generation), vector databases, and knowledge management systems to improve contextual responses.
• Monitor AI application performance and implement prompt improvements based on user feedback.
• Document prompt engineering methodologies, testing results, and governance standards.

Required Skills

• Strong understanding of Generative AI, LLMs, and Prompt Engineering concepts.
• Hands-on experience with OpenAI/ Anthropic Claude or similar AI platforms.
• Knowledge of prompt patterns such as:
• Zero-shot
• Few-shot
• Chain-of-Thought (CoT)
• Tree-of-Thought (ToT)
• ReAct
• Role-based prompting
• Experience with Python and AI development frameworks.
• Familiarity with any of the frameworks like LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent frameworks.
• Understanding of RAG architectures and vector databases such as Pinecone etc
• Strong analytical and problem-solving skills.
• Excellent communication and documentation abilities.