> Markdown version of [/jobs/ext/1454216-prompt-engineer-jersey-city-nj-hybrid-4-days-onsite](https://www.wearedevelopers.com/jobs/ext/1454216-prompt-engineer-jersey-city-nj-hybrid-4-days-onsite). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Prompt Engineer || Jersey City, NJ (Hybrid - 4 Days Onsite)

- **Company:** United Software Group, Inc.
- **Location:** Jersey City, NJ, United States
- **Experience:** Expert
- **Salary:** $225,000.0 - $280,000.0
- **Contract:** Temporary to permanent
- **Skills:** A/B Testing, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Automation of Tests, Microsoft Azure, Content Analysis, Continuous Integration, Information Leak Prevention, Software Debugging, Knowledge Management, Natural Language Processing, Management of Software Versions, Data Processing, Chatbots, Microsoft Power Automate, Delivery Pipeline, Large Language Models, Multi-Agent Systems, Prompt Engineering, Generative AI, AI Platforms, Powerapps
- **Published:** July 26, 2026
- **Apply:** https://www.careerjet.com/jobad/usb136bdbb3794759b141f9ba480b01643

## About the Role

* Strong understanding of Large Language Models (LLMs), prompt engineering, prompt optimization, tokenization, context windows, embeddings, Retrieval-Augmented Generation (RAG), model behavior, and Generative AI limitations.
 * Hands-on experience with one or more enterprise AI platforms such as OpenAI APIs, Azure OpenAI, AWS Bedrock, Anthropic Claude, LangChain, Semantic Kernel, LlamaIndex, Microsoft Copilot Studio, Power Platform, or similar frameworks.
 * Experience designing and optimizing system prompts, few-shot prompts, prompt templates, conversation flows, response formatting, and structured AI interactions for production applications.
 * Ability to evaluate and debug LLM behavior using structured testing, error analysis, prompt experimentation, prompt evaluation frameworks, and iterative optimization.
 * Strong understanding of prompt security, including prompt injection, jailbreak attacks, sensitive data leakage, hallucinations, instruction conflicts, unauthorized tool usage, and Responsible AI principles.
 * Excellent communication, analytical thinking, technical writing, stakeholder management, and collaboration skills.
 * Experience creating repeatable prompt libraries, evaluation evidence, governance documentation, and enterprise prompt standards.

Preferred Experience

 * Background in Natural Language Processing (NLP), Conversational AI, UX Writing, Technical Writing, Product Design, Knowledge Management, Business Analysis, Information Architecture, or Enterprise AI.
 * Experience within Banking, Financial Services, Insurance, FinTech, Compliance, Risk Management, Legal, Customer Support, Operations, Knowledge Management, or Enterprise Productivity domains.
 * Experience with Microsoft Copilot Studio, Power Platform, prompt registries, prompt lifecycle management, A/B testing, human-in-the-loop review workflows, evaluation tooling, and Responsible AI governance.
 * Familiarity with enterprise AI development practices including RAG architecture, embeddings, vector databases, AI orchestration frameworks, and LLM evaluation platforms.

## Description

The Prompt Engineer will design, test, optimize, govern, and continuously improve prompts, system instructions, conversation flows, and interaction patterns for AIRP Large Language Model (LLM) applications and enterprise Generative AI solutions. This role is responsible for ensuring AI-generated responses are accurate, grounded, explainable, consistent, secure, cost-efficient, and aligned with enterprise business objectives, governance policies, compliance requirements, and Responsible AI principles.
The organization is building enterprise-grade AI capabilities, and this role focuses on creating production-ready prompt engineering practices that support business-critical use cases rather than generic chatbot experimentation. The engineer will develop reusable prompt patterns for AIRP and enterprise Microsoft Copilot Studio, Power Platform, Power Apps, and Power Automate citizen-development initiatives while ensuring proper prompt security, sensitive data handling, grounding with citations, structured evaluation, and governance.
The successful candidate will own the design and governance of prompt libraries, system prompts, response templates, conversation policies, prompt versioning, evaluation frameworks, quality metrics, and reusable guardrail patterns for enterprise AI applications. Working closely with AI Engineers, Product Managers, Data Scientists, UX teams, and business stakeholders, the Prompt Engineer will continuously improve AI interactions through structured testing, experimentation, production monitoring, and iterative optimization., * Design, develop, and optimize prompts, system instructions, conversation flows, response templates, and interaction patterns for enterprise LLMs, chatbots, copilots, RAG systems, document intelligence, workflow automation, AI agents, knowledge assistants, and decision-support applications.

 * Develop system prompts, few-shot learning examples, tool-use instructions, conversation policies, citation strategies, response formatting standards, escalation logic, and structured output templates that deliver consistent, accurate, and business-aligned AI responses.
 * Create and optimize prompts for enterprise business use cases including KYC support, credit underwriting, governance tracking, pitch book generation, Banker 360, Customer 360, deal intelligence, financial crime detection, sanctions screening, enterprise knowledge management, and document analysis.
 * Build and maintain reusable prompt libraries, prompt templates, guardrail patterns, prompt registries, and enterprise prompt standards that support AIRP applications and Microsoft Copilot Studio / Power Platform citizen-development initiatives.
 * Evaluate prompt performance using structured metrics including task success rate, groundedness, hallucination rate, factual accuracy, completeness, citation quality, safety, latency, token utilization, response consistency, user satisfaction, and operational cost.
 * Partner with AI Engineers and platform teams to implement prompt versioning, automated testing, A/B testing, CI/CD integration, deployment workflows, monitoring, rollback strategies, and production governance.
 * Improve Retrieval-Augmented Generation (RAG) quality by evaluating retrieval relevance, document chunking strategies, embedding quality, context selection, citation behavior, response synthesis, grounding, and missing-context handling.
 * Conduct adversarial prompt testing to identify and mitigate prompt injection, jailbreak attacks, instruction conflicts, sensitive data leakage, hallucinations, unsafe outputs, unauthorized tool usage, and prompt security vulnerabilities.
 * Collaborate with Product, Engineering, UX, Business, Compliance, Legal, and Responsible AI teams to ensure prompt designs meet enterprise governance, regulatory, security, privacy, and business requirements.
 * Document prompt engineering best practices, evaluation methodologies, governance evidence, and optimization strategies to support enterprise AI standards and Responsible AI initiatives.


## Related Videos

- [Bringing the power of AI to your application.](https://www.wearedevelopers.com/videos/1010-bringing-the-power-of-ai-to-your-application)
- [The Power of Prompting with AI Native Development - Simon Maple](https://www.wearedevelopers.com/videos/1330-the-power-of-prompting-with-ai-native-development-simon-maple)
- [Chatbots are going to destroy infrastructures and your cloud bills](https://www.wearedevelopers.com/videos/1130-chatbots-are-going-to-destroy-infrastructures-and-your-cloud-bills)
- [Using LLMs in your Product](https://www.wearedevelopers.com/videos/1186-using-llms-in-your-product)
- [Testing AI Agents: Automated Evaluation for Chatbots & RAG Systems](https://www.wearedevelopers.com/videos/100300-testing-ai-agents-automated-evaluation-for-chatbots-rag-systems)
- [Beyond Autocomplete: Local AI Code Completion Demystified](https://www.wearedevelopers.com/videos/961-beyond-autocomplete-local-ai-code-completion-demystified)

## Related Articles

- [The Prompt Engineer ✍️](https://www.wearedevelopers.com/magazine/216-the-prompt-engineer)
- [Prompt Engineering is a Job of the Past](https://www.wearedevelopers.com/magazine/342-prompt-engineering-is-a-job-of-the-past)
- [How to Bypass ChatGPT’s Filter With Examples](https://www.wearedevelopers.com/magazine/332-how-to-bypass-chatgpt-s-filter-with-examples)
- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)
- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)