GenAI Prompt Engineering

Latitude; New York (NY); On-site; USD 140,000 - 220,000; Full time

Job summary

Moonfire is seeking an experienced GenAI Prompt Engineer in New York to design, test, and optimize prompts for LLM-powered chatbots, agents, and RAG systems. You will translate business needs into reliable prompt workflows, ensuring accuracy, security, and measurable performance improvements.

You will collaborate with product, engineering, and data science teams to implement prompts, evaluate outcomes, and continuously refine agent workflows with a focus on safety and robustness.

Qualifications

• 5+ years in Software, Data, or Applied AI roles.
• Minimum 1+ year hands-on LLM prompt engineering experience in production.
• Strong Python scripting and API integration experience.
• Hands-on experience with GPT and Claude.
• Experience with LLM orchestration tools such as LangChain.
• Experience designing evaluation frameworks and improving LLM performance.
• Working knowledge of RAG architectures and AI agent patterns.
• Experience with tool calling and agent workflows.
• Strong data analysis skills to interpret evaluation results.

Responsibilities

• Design, test, and refine prompts to maximize accuracy, relevance, and consistency.
• Build evaluation frameworks, including A/B testing, benchmarking, golden datasets, and rubric-based scoring.
• Apply strong knowledge of LLM behavior, context windows, tokenization, and fine-tuning versus prompting.
• Collaborate with product, engineering, and data science teams to design prompt and agent workflows.
• Implement prompt security and safety measures, including jailbreak prevention, bias mitigation, and guardrails.
• Maintain prompt versioning, regression testing, and continuous optimization.

Skills

Prompt engineering

Python

LLM integration

Data analysis

Collaboration

Tools

LangChain

API integration

GPT/Claude

Job description

We are seeking an experienced GenAI Prompt Engineer to design, develop, test, and optimize prompts for LLM-powered chatbots, AI agents, and Retrieval-Augmented Generation (RAG) systems.

The candidate will translate business requirements into reliable prompt and agent workflows while ensuring accuracy, consistency, security, and measurable performance improvements.

Key Responsibilities:

• Design, test, and refine prompts to maximize accuracy, relevance, and consistency.
• Build evaluation frameworks, including A/B testing, benchmarking, golden datasets, and rubric-based scoring.
• Apply strong knowledge of LLM behavior, context windows, tokenization, and fine-tuning versus prompting.
• Collaborate with product, engineering, and data science teams to design prompt and agent workflows.
• Implement prompt security and safety measures, including jailbreak prevention, bias mitigation, and guardrails.
• Maintain prompt versioning, regression testing, and continuous optimization.

Required Qualifications & Technical Skills:

• 5+ years of experience in Software, Data, or Applied AI roles.
• Minimum 1+ year of hands-on LLM prompt engineering experience in production.
• Strong Python scripting and API integration experience.
• Hands-on experience with GPT and Claude.
• Experience with LLM orchestration tools such as LangChain.
• Experience designing evaluation frameworks and improving LLM performance.
• Working knowledge of RAG architectures and AI agent patterns.
• Experience with tool calling and agent workflows.
• Strong data analysis skills to interpret evaluation results.