Senior Prompt Architect for LLM & GenAI Systems

Photon; New York (NY); On-site; USD 120,000 - 180,000; Full time

Job summary

Photon in New York is seeking a Senior Prompt Engineer to design, develop, test, and optimize prompts and interaction strategies for Large Language Models and Generative AI applications. You will work with AI/ML engineers, data scientists, software engineers, product managers, and stakeholders to deliver reliable, scalable AI solutions.

The ideal candidate has hands-on experience with prompt engineering, LLMs, RAG, evaluation, AI agents, and Python, with a proven ability to translate complex

Qualifications

• Hands-on experience designing prompts for large language models and generative AI systems.
• Ability to translate business needs into effective AI instructions and workflows.
• Experience with evaluation frameworks and prompt testing.

Responsibilities

• Design, develop, test, and optimize prompts for LLM-powered applications.
• Create system prompts, templates, and multi-step prompt workflows.
• Apply zero-shot, few-shot, and structured prompting techniques.
• Develop prompts for structured outputs (JSON/schema) and RAG-based apps.
• Collaborate with engineering teams to improve retrieval context and grounding.
• Design strategies for AI agents and tool/function calling.
• Build evaluation/testing frameworks to measure quality, latency, and cost.
• Create evaluation datasets, test cases, and benchmarks for GenAI use cases.
• Identify and reduce hallucinations and irrelevant outputs.
• Maintain prompt versioning and reusable prompt libraries.
• Integrate prompts into production applications and APIs.

Skills

Prompt Engineering

LLMs

Generative AI

RAG

Python

Prompt evaluation

AI agents

Prompt versioning

Job description

Photon in New York is seeking a Senior Prompt Engineer to design, develop, test, and optimize prompts and interaction strategies for Large Language Models and Generative AI applications. You will work with AI/ML engineers, data scientists, software engineers, product managers, and stakeholders to deliver reliable, scalable AI solutions.

The ideal candidate has hands-on experience with prompt engineering, LLMs, RAG, evaluation, AI agents, and Python, with a proven ability to translate complex